A job recommendation method and system

Abstract

The present invention provides a job recommendation method, comprising the following steps S1: obtaining user access data and generating a data matrix; step S2: performing a supervised learning algorithm on the data matrix; and step S3: performing an unsupervised learning algorithm on the data matrix and generating prediction result data ; Step S4: Generate job pre-recommendation data according to the prediction result data and the portrait data. The beneficial effect of the present invention is that according to the visitor's equipment information, access content, operation behavior, etc., through the machine learning method of position pre-recommendation, the system can automatically learn, complete user analysis, and accurately recommend job information; let users find more relevant information. Highly popular and interested job information, improve user viewing content, and thus have a high user conversion rate.

Description

technical field [0001] The present invention relates to the technical field of the Internet, in particular to a job recommendation method and system. Background technique [0002] With the popularization of the Internet, job hunting and job hunting have gradually shifted from the traditional talent market to online job hunting methods such as the Internet and mobile Internet; according to monitoring data analysis, nearly 90% of the visiting personnel have not logged in to the system, and about 40% of the logged-in users have not. Clear job-seeking intentions; for this part of users, due to the lack of input of relevant information and unclear job-seeking intentions, the system cannot judge the content that users need, and the recommended information is general information, and there is no relevant information about recommended visiting users, which may easily cause user loss; The existing technical solution is to recommend similar jobs according to the classification of the ...

AI Technical Summary

Problems solved by technology

[0002] With the popularization of the Internet, job hunting and job hunting have gradually shifted from the traditional talent market to online job hunting methods such as the Internet and mobile Internet; according to monitoring data analysis, nearly 90% of the visiting personnel have not logged in to the system, and about 40% of the logged-in users have not. Clear job-seeking intentions; for this part of users, due to the lack of input of relevant information and unclear job-seeking intentions, the system cannot judge the content that users need, and the recommended information is general information, and there is no relevant information about recommended visiting users, which may easily cause user loss; The existing technical solution is to recommend similar jobs according to the classification of the viewed job information after the user clicks to view the job; Rough, unable to carry out precise marketing to visiting job seekers

[0003] The existing technical solution is to recommend based on similar positions, without analyzing the user's operation behavior, not knowing the user's characteristics, and the recommendation method is rough; the information recommended in this way is quite different from the user's needs; in addition, some job seekers have unclear job intentions , there is a mismatch of recommended information and no guidance for such users, resulting in the loss of a large number of users

[0004] The automatic recommendation products in the prior art do not deeply combine job hunting and user characteristics; they cannot accurately recommend jobs to job seekers, and the user conversion rate is low

Images