Method for judging gender of Chinese name based on multi-layer perceptron

Abstract

The invention belongs to the technical field of artificial intelligence, and particularly discloses a method for judging gender of a Chinese name based on a multilayer perceptron, which comprises thefollowing specific steps: obtaining an initial character vector and a word vector of a character for the Chinese name on a character and word vector training corpus by using word2vec; dividing the Chinese name corpus into a training corpus and a test corpus according to a certain proportion, wherein the training corpus is divided into a training corpus and a verification corpus according to a certain proportion; establishing a multi-layer perceptron model and training the multi-layer perceptron model for judging the gender of the Chinese name; and inputting a Chinese name of which the gender is to be judged, and carrying out gender judgment and subsequent statistical treatment. According to the judging method, the gender of the user is judged only through the name of the user, original data are easy to obtain, the character features of the Chinese names of different genders of men and women are automatically obtained by means of the multi-layer perceptron, manual participation in feature engineering is not needed, and a large amount of manpower is saved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method for judging the gender of a Chinese name based on a multilayer perceptron. Background technique [0002] The gender of users in the network environment is very important information. Users of different genders need to be treated differently in many scenarios such as content push, online marketing, product recommendation, and advertisement delivery. For example, at present, online shopping has become the choice of more and more consumers, and there are great differences in the online shopping behavior of consumers of different genders. Users of different genders are treated differently. On the other hand, it is easy for an online shopping platform to obtain the user's real name, and it is generally not convenient to obtain the user's gender information. Can the user's gender information be predicted from the user's name? The answer is affirma...

AI Technical Summary

Problems solved by technology

[0004] The document "A Gender Judgment Method Based on Characteristic Features of Chinese Names" published in the Journal of Shandong University in 2014 proposes a method for judging the gender of Chinese names using a naive Bayesian classifier. Character features and their combinations are used for statistical analysis, and manual participation in feature engineering is more time-consuming and labor-intensive.

In view of the fact that it is impossible to obtain the user's personalized domain name or body image in many scenarios, and manual feature engineering is time-consuming and laborious, this invention proposes a Chinese name gender determination method based on a multi-layer perceptron, which can be used for user gender determination

Images