Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A job and talent matching and recommending method for human resource enterprises

A technology of human resources and recommendation methods, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve the problems of failure to consider the individual needs of job seekers, lack of understanding of keyword retrieval efficiency, lack of detailed description of recommendation algorithms, etc. question

Pending Publication Date: 2019-06-14
JINAN UNIVERSITY
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the current search engines are based on word matching, and this kind of word matching must have the following three problems: 1. The matching of most keywords is an exact matching search, and the returned results are the same for all job seekers. Taking into account the individual needs of different job seekers; 2. Most job seekers are not familiar with information retrieval technology, and do not know how to improve retrieval efficiency by better constructing keywords. The keywords constructed by job seekers may have too broad meanings. It may also be too specific, resulting in low search quality; 3. The search results may contain hundreds or even thousands of recruitment information, and job seekers generally only pay attention to the first few dozens
[0007] This invention is similar to the scheme idea of ​​the present invention, but there is no detailed description of the recommendation algorithm therein, and there is no part of using expert experience proposed by the scheme of the present invention

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A job and talent matching and recommending method for human resource enterprises
  • A job and talent matching and recommending method for human resource enterprises
  • A job and talent matching and recommending method for human resource enterprises

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] The present invention provides a position and talent matching and recommendation method for a human resource enterprise, specifically including a collaborative filtering recommendation scheme, an expert wisdom-based recommendation scheme and an integration scheme;

[0085] (1) Collaborative filtering recommendation scheme

[0086] Record the interaction history of the form {(u t ,O t ,D t )}, where t is the index subscript of a specific interactive session, build a recommendation system, and define the problem of collaborative competitive filtering as: Consider the user-system interaction process in the recommendation system as follows: There is a user u∈U:= {1,2,3,...,M} and item i∈I:={1,2,3,...,N}, where U represents the entire user space, I represents the entire item space, and O t Represents a user-selectable context or set of offers, D t represents the set of items that the user makes a decision on, and i * means D t an item in the collection;

[0087] When ...

Embodiment 2

[0149] In the job recommendation idea described above, the application records well reflect the job seekers’ preference for the job they are applying for. This preference can be calculated using the hidden factor model method, that is, assume that all aspects of the job can be represented by a vector, and use The other vector represents the job seeker's preference for various characteristics. The inner product of the two vectors is calculated, and the result can represent the job seeker's overall preference for the job. The larger the value, the more the job seeker likes the job. The more the position is recommended to job seekers;

Embodiment 3

[0151] The job recommendation based on expert wisdom is essentially a collaborative recommendation based on expert users. In the massive data, some experts who are similar to the target user’s hobbies are found as neighbors. Pearson similarity is used to calculate the similarity between job seekers, and then Composing a sequence of jobs that these neighbors like to recommend to target users is called the nearest neighbor model, and related algorithms have been made public, so I won’t repeat them here;

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a job and talent matching and recommending method for human resource enterprises, and particularly relates to the field of network recruitment. The method specifically comprises a collaborative filtering recommending scheme, an expert-based intelligent recommending scheme and an integrating scheme. According to the method, a job seeker does not need to input accurate searchkeywords, so that the process that the job seeker constructs appropriate keywords is omitted, the problem caused by the fact that retrieval needs to depend on accurate matching of query keywords is solved. The job recommendation scheme recommends the job information which the job seeker may be interested in to for the job seeker; so that the effects of interacting in an offline manner and actively pushing are realized. Through the position recommendation, the recruitment website can periodically and actively push positions which a job seeker may be interested in to an e-mail box or a mobile phone registered by the job seeker; wherein one of the purposes of position retrieval is to filter positions with low relevancy and low interest of job seekers, and the recommendation result of the positions interested by the user is generally dozens of positions, so that the information overload burden of the user can be reduced through the method.

Description

technical field [0001] The invention relates to the technical field of network recruitment, and more specifically, the invention relates to a position and talent matching and recommendation method of a human resource enterprise. Background technique [0002] At present, a typical job-seeking interaction process of online recruitment is roughly as follows: recruiters publish job information through the online recruitment platform, and then wait for job seekers to apply. After job seekers complete their resumes on the online recruitment platform, they search for relevant job information through the platform's search engine, and then select the jobs they are interested in for delivery. After receiving the application for the position, the recruiter reviews whether the resume of the job seeker meets the requirements of the position. If the resume meets the requirements, a further understanding is carried out. The common way is to make an appointment for an interview. Otherwise ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9535G06Q10/10
Inventor 朱蔚恒龙舜樊广源蔡跳王会进
Owner JINAN UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com