Resume duplicate checking method and resume duplicate checking system

Abstract

The invention discloses a resume duplicate checking method and a resume duplicate checking system. The method comprises the steps: a recruiter client obtains a resume text to be subjected to duplicate checking, and sends the resume text to a recruiter server; the recruiter server performs segmented text processing on the resume text to generate text segments to be subjected to duplicate checking; the recruiter server initiates a duplicate checking request after generating a text segment, and sends the text segment to a duplicate checking receiving server; the duplicate checking receiving server pushes the received text segments into a queue for duplicate checking; the crawler server sequentially reads to-be-crawled text segments from the queue, and performs searching, crawling, matching and data processing on each text segment in a search engine to obtain a first text having the highest similarity with each text segment; the crawler server side sends the first text to the recruiter server side; and the recruiter server calculates the duplicate checking rate of the resume according to the similarity between each first text and the corresponding text segment. According to the method, the time for resume duplicate checking is shortened, and the accuracy of resume duplicate checking results is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a resume checking method and a resume checking system. Background technique [0002] Because online recruitment has the advantages of wide coverage, strong timeliness, and low cost, most companies currently recruit through the Internet. Compared with traditional offline recruitment, online recruitment can enable enterprises to receive a large number of resumes, so that they can have a better chance of recruiting excellent talents, but a large number of resumes will reduce recruitment efficiency, especially now that resumes plagiarize Internet information is more common Under such circumstances, it takes a lot of manpower and time to select talents. [0003] Currently, there are few solutions on the market to identify plagiarism in resumes. There is a hash signature matrix scheme on the market that can only query similar resumes from the resume database according...

AI Technical Summary

Problems solved by technology

But for a newly submitted resume, the information in the resume is basically irrelevant to the information in the existing resume database

If a candidate plagiarizes a piece of text on the Internet, and this text has never appeared in the existing resume database, it cannot be identified. It can be seen that the limitation of this method is relatively large, and the purpose of plagiarism judgment cannot be achieved.

In addition, most companies currently search and judge the entire resume text manually. Based on the search rules of search engines on the market, the entire text search may fail to search or the search results are inaccurate, which wastes unnecessary time and energy and increases Additional workload, if the resume text is divided manually, there will be a large workload, high repetition rate, and different judgment rules, which will not improve the efficiency of recruitment and meet the needs of resume plagiarism judgment

Images