Text-based similarity determination method, device and computer equipment

Abstract

The invention relates to a text-based similarity determination method and device, and belongs to the technical field of the Internet. The method includes: acquiring historical web browsing records of candidate users, and obtaining a text set corresponding to the candidate user according to the historical web browsing records; acquiring the pre-calculated text set in which each text falls into the text set corresponding to the reference user conditional probability; according to the text set corresponding to the candidate user and the conditional probability of each text, obtain the first text feature vector corresponding to the candidate user; input the first text feature vector of the candidate user into the pre-trained random A forest model, obtaining the similarity value between the candidate user and the reference user according to the output of the random forest model. The above technical solution solves the problem that the similarity between users cannot be accurately calculated, and can accurately calculate the similarity between the candidate user and the reference user through the relevant information of the text, and then can find similar users to the reference user.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a text-based similarity determination method, device, computer-readable storage medium and computer equipment. Background technique [0002] Currently, finding similar users and pushing messages or sending advertisements to similar users has become an effective marketing method. The premise of this marketing method is to accurately determine and calculate the similarity between users. Traditional text-based methods for determining similarity include k-means clustering, etc. In the process of realizing the present invention, the inventor found that there are at least the following problems in the prior art: the traditional method for determining similarity is not suitable for determining similarity based on words; Clustering by batches of users gives different results. Therefore, it is necessary to find a method that can calculate the similarity between users through the r...

AI Technical Summary

Problems solved by technology

In the process of realizing the present invention, the inventor found that there are at least the following problems in the prior art: the traditional method for determining similarity is not suitable for determining similarity based on words; Batches of users clustering give different results

Images