User recommendation model training method and device, computer equipment and storage medium

Abstract

The invention relates to a user recommendation model training method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a plurality of user pairsfrom a database as training samples; Determining a sample target value of each training sample and a target level of the sample target value according to the interaction type of the user pair; Extracting sample characteristics of the training samples to obtain corresponding sample characteristics; Inputting the sample characteristics into a recommendation model, wherein the recommendation model determines the sequence of each training sample through the sample characteristics; When the matching rate of the sequence of each training sample and the target level reaches the preset accuracy, the trained recommendation model is obtained, and through the recommendation model trained in this way, the passive party with the high matching degree can serve as the recommendation user of the active party, so that the recommendation accuracy is greatly improved.

Description

Technical field [0001] This application relates to the field of machine learning technology, and in particular to a training method, device, computer equipment and storage medium for a user recommendation model. Background technique [0002] With the development of computer technology, artificial intelligence technology has also entered a period of rapid development. Machine learning is one of the branches of artificial intelligence technology. Machine learning learns from a large amount of data, so that it can predict and classify the input data. On the Internet dating platform, user recommendations can also be achieved through machine learning. For example, you can recommend friends for newly registered users through machine learning to increase the interactivity and adhesion of new users. [0003] In traditional technology, the friend-making platform generally adopts a user recommendation method based on collaborative filtering, that is, calculating the similarity between two...

AI Technical Summary

Problems solved by technology

[0004]However, this method of marriage and love recommendation based on collaborative filtering has the problem of data sparsity and cold start, that is, most users have no interactive behavior, and There is no connection. If it is a newly registered user, there is no historical interaction data at all. Therefore, this recommendation method cannot recommend a truly suitable and suitable user for the user in need, and the accuracy of the recommendation is low.

Images