Friend-making scene-based recommendation model training method and device, electronic equipment and computer readable storage medium

Abstract

The invention relates to a friend-making scene-based recommendation model training method and device, electronic equipment and a computer readable storage medium. The method comprises the steps of: obtaining a user behavior data set of a friend-making recommendation page of a target application program within a preset time; screening a first sample set from the user behavior data set to train a preset click rate estimation model, and obtaining the click rate estimation model, wherein the click rate estimation model outputs click probability parameters obtained by executing maximum likelihood calculation on the user behavior data set; performing initialization on a recommendation model to be trained based on the click probability parameter to obtain an initialized recommendation model; and constructing a second sample set based on a user behavior data set, and substituting the second sample set into the initialized recommendation model for training to obtain the recommendation model. The embodiment of the invention has the advantage of improving the accuracy of the recommendation model.

Description

Technical field [0001] The present application relates to the field of machine learning, and in particular, there is a training method, device, electronic device, and computer readable storage medium based on a recommendation model based on dating scene. Background technique [0002] With the in-depth research of computer technology, artificial intelligence technology also develops rapidly, machine learning is an important part of artificial intelligence technology, where the recommended model is one of the most widely used models in the machine learning model. One of the main application scenarios of the recommendation model is the social dating platform. [0003] At present, the recommended model in the social dating platform is usually the SVMRANK model constructed by the SVM of the Support Vector Machine. Its main reduction sorting problem is transformed into the Pairwise classification problem and then uses the SVM classification model to learn and solve, that is, during the...

AI Technical Summary

Problems solved by technology

However, in the process of training the recommendation model through the pairwise algorithm, the sample quality is extremely high, and it is easy to generate wrong labels in the process of constructing the training pair, which leads to the poor effect of the trained recommendation model. Moreover, training through the pairwise algorithm The recommended model only learns local sorting, but cannot learn the global sample, and its versatility is poor, so the training effect of the recommended model is low, and the accuracy rate is not high

Images