Employment recommendation system and method based on big data

Abstract

The invention discloses an employment recommendation system and method based on big data, relates to the technical field of computers, and solves the technical problem that the employment recommendation system is low in use satisfaction degree due to the fact that resume delivery of job seekers is lack of pertinence because it is difficult to sort according to the popularity and time urgency of recruitment posts in an existing scheme. According to the invention, resume basic information of a plurality of job seekers and recruitment post information of a plurality of employment enterprises are collected; obtaining historical browsing records and recruitment deadlines of posts published by a plurality of employment enterprises in the recruitment software platform; analyzing the recruitment post information of each employment enterprise to obtain a post classification set; and generating an employment post recommendation sequence based on the post matching degree, the post popularity and the recruitment deadline. According to the scheme, the employment recommendation result is accurate, the correlation is high, and the post recommendation satisfaction degree of the employment recommendation system can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of computer technology, and in particular relates to an employment recommendation system and method based on big data. Background Art

[0002] With the rapid development of internet technology and the ever-changing job market, traditional job recommendation methods are no longer able to meet the growing demand for matching job seekers with employers. While most recruitment platforms currently have a vast database of candidate resumes and company recruitment information, a lack of effective data mining and intelligent analysis methods results in job recommendations with low matching accuracy, slow response times, limited personalization, and poor timeliness. On the one hand, job seekers often face information overload, struggling to quickly find positions that closely match their skills and interests. On the other hand, employers struggle to accurately reach high-quality candidates who meet job requirements, impacting recruitment efficiency and the quality of job matching.

[0003] Existing technologies work by matching job seekers' resumes with employers' job requirements to recommend matching positions to the corresponding applicants. However, in practice, existing solutions struggle to prioritize job openings based on their popularity and timeliness, resulting in a lack of targeted resume submissions and low user satisfaction with job recommendation systems. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an employment recommendation system and method based on big data, which is used to solve the technical problem that existing solutions are difficult to sort according to the popularity and time urgency of recruitment positions, resulting in a lack of targeting in the submission of job seekers' resumes, thereby leading to low user satisfaction with the employment recommendation system.

[0005] To achieve the above objectives, the first aspect of the present invention provides a method for job recommendation based on big data, comprising: Collect basic resume information of several job seekers and job posting information of several employing companies; and obtain historical browsing records and recruitment deadlines of job postings posted by several employing companies on recruitment software platforms; Determine the popularity of each job post based on historical browsing records; Analyze the basic information of each job seeker's resume to obtain a resume classification set; Analyze the recruitment information of each employing company to obtain a set of job classifications; Determine the job matching degree between each job seeker and each recruitment position based on the resume classification set and the position classification set; Generate a job recommendation sequence based on job matching, job popularity, and recruitment deadline.

[0006] Preferably, determining the popularity of each recruitment position based on historical browsing records includes: Determine the popularity of each job post based on historical browsing history, including: Extract the historical browsing records of the job positions posted by each employing company on the recruitment software platform; the historical browsing records are composed of several job browsing records; Eliminate invalid data from historical browsing records to obtain valid browsing data; valid browsing data includes valid clicks, valid collections, and valid interview invitation rates; Obtain the probationary period resignation information for each recruitment position, and calculate the probationary period voluntary resignation rate for each recruitment position based on the probationary period resignation information; By formula Calculate the job heat GWRi of recruitment position i; where, is the effective click volume of recruitment position i, is the effective collection volume of recruitment position i, is the effective interview invitation rate for recruitment position i, is the voluntary turnover rate during the probation period of recruitment position i; a1, a2, a3, and a4 are all proportional coefficients greater than 0; i=1, 2,…, n, where n is the total number of employing companies.

[0007] Preferably, the step of removing invalid data from the historical browsing records includes: Obtain interview records for each job post and several job browsing records from historical browsing records; job browsing records include job seekers' browsing time, clicks, and favorites for the job post; interview records include the number of interview invitations and interview cancellations received from the employing company; Determine whether the job seeker is an employee of the employing company to which the recruitment position belongs; if yes, mark the corresponding position browsing record as invalid browsing record; if not, mark the corresponding position browsing record as valid browsing record; Determine whether the browsing time in the valid browsing record is greater than the preset time threshold; if yes, mark the click behavior of the corresponding job browsing record as a valid click; if not, mark the click behavior of the corresponding job browsing record as an invalid click; Determine whether the basic information of the job seeker's resume corresponding to the valid browsing record meets the hard requirements of the recruitment position; if yes, mark the collection behavior in the job browsing record as valid; if not, mark the collection behavior in the job browsing record as invalid; where hard requirements refer to the prerequisites that must be met for joining the recruitment position; The total number of valid clicks is marked as valid clicks, and the total number of valid collections is marked as valid collections; Calculate the effective interview invitation rate for each recruitment position based on the effective click volume and interview records.

[0008] Preferably, the calculation of the effective interview invitation rate for each recruitment position based on the effective click volume and interview records includes: Extract the effective click volume and interview records of each recruitment position; Calculate the difference between the number of interview invitations and the number of interview cancellations in the interview records of each recruitment position to obtain the number of valid interview invitations for each recruitment position; Calculate the ratio of the number of effective interview invitations to the effective click volume for each recruitment position to obtain the effective interview invitation rate for each recruitment position.

[0009] Preferably, the calculation of the voluntary turnover rate during the probation period of each recruitment position based on the probation period resignation information includes: Obtain probationary period resignation data for each recruiting position posted by each employer within the most recent consecutive cycles. This probationary period resignation data includes the total number of employees who resigned and the type of resignation, including voluntary resignation and resignation due to incompetence. Calculate the ratio of the number of employees who voluntarily resigned from each recruitment position to the total number of employees who resigned, and obtain the voluntary turnover rate during the probation period of each recruitment position.

[0010] Preferably, the basic information of each job seeker's resume is analyzed to obtain a resume classification set, including: Extract basic resume information of each job seeker; basic resume information includes intended position and personal information, and personal information includes education, major, age, years of work experience, skills information, and certification information; The basic information of several resumes with the same intended position is added into a resume sequence, and several resume sequences are integrated into a resume classification set.

[0011] Preferably, the analysis of the recruitment position information of each employing enterprise to obtain a position classification set includes: Extract recruitment information from various employers; recruitment information includes job titles and hiring requirements, including educational requirements, major requirements, age requirements, years of work experience requirements, skills requirements, and certification requirements; Add several recruitment position information with the same position title into a recruitment position sequence, and integrate several recruitment position sequences into a position classification set.

[0012] Preferably, the determining of the job matching degree between each job seeker and each recruitment position based on the resume classification set and the position classification set includes: Extracting a resume classification set and a position classification set; matching the intended positions of each job application resume sequence in the resume classification set with the position titles of each recruitment position sequence in the position classification set to obtain a matching result; wherein the matching result includes a matching success and a matching failure; If the matching result is successful, the job seeker's personal information will be matched with the recruitment requirements of the corresponding recruitment position to obtain several job matching scores; among which, the job matching scores include academic qualifications score, major score, age score, years of work experience score, skills score, and certificate score; Calculate the sum of the products of several job matching scores and corresponding weight coefficients to obtain the job matching degree; If the matching result is a match failure, the job matching degree between the corresponding job seeker and the corresponding recruitment position will be marked as 0.

[0013] Preferably, generating a job recommendation sequence based on job matching degree, job popularity, and recruitment deadline includes: Extract the job matching degree between each job seeker and each recruitment position, the job popularity and recruitment deadline of each recruitment position posted by each employer; Determine whether the job matching degree is greater than a preset matching degree threshold; if yes, mark the corresponding recruitment position as a recommended position for the corresponding job seeker; if no, mark the corresponding recruitment position as an unmatched position for the corresponding job seeker; Integrate multiple positions to be recommended into a sequence of positions to be recommended; Sort the recommended job sequences in descending order of job matching degree to obtain the first recommended sequence; Sort the recommended job sequences in descending order of job popularity to obtain the second recommended sequence; Sort the recommended positions in ascending order of recruitment deadlines to obtain the third recommendation sequence; The first recommendation sequence, the second recommendation sequence and the third recommendation sequence are integrated into a job recommendation sequence.

[0014] A second aspect of the present invention provides an employment recommendation system based on big data, comprising: a data processing module, and a data collection module and an employment recommendation module connected thereto; The data collection module is used to collect basic resume information of several job seekers and recruitment information of several employing companies; and obtain historical browsing records and recruitment deadlines of recruitment positions posted by several employing companies on the recruitment software platform; The data processing module is used for determining post heat degrees of various recruitment posts based on historical browsing records; analyzing resume basic information of various job seekers to obtain a resume classification set; and analyzing recruitment post information of various employing enterprises to obtain a post classification set; The employment recommendation module is used for determining post matching degrees between various job seekers and various recruitment posts based on the resume classification set and the post classification set; and generating an employment post recommendation sequence based on the post matching degrees, the post heat degrees and recruitment deadlines.

[0015] Compared with the prior art, the present application has the following beneficial effects: 1. The present application constructs a multi-dimensional and dynamic person-post matching model by collecting resume basic information of job seekers, recruitment post information of employing enterprises and historical browsing records and recruitment deadlines of posts on a recruitment platform; improves the structured recognition and matching ability of the system for the characteristics of job seekers and posts by classifying and analyzing the resume and post information; calculates the post heat degrees based on the post browsing data, which can reflect the competition degree of the post and the urgency of the enterprise recruitment, thereby enhancing the real adaptability and guiding significance of the recommendation result; further improves the timeliness judgment ability of the recommendation system in combination with the recruitment deadlines; and finally, generates an employment post recommendation sequence by comprehensively considering the post matching degrees, the post heat degrees and the time factors, so that the recommendation result is not only accurate and highly relevant, but also facilitates the targeted delivery of the recruitment post by the job seekers, thereby being beneficial to improving the post recommendation satisfaction of the employment recommendation system.

[0016] 2. The present application improves the accuracy and practicality of the recruitment data analysis by effectively eliminating invalid data in the historical browsing records. First, whether the job seeker is an employee of the employing enterprise of the recruitment post is judged, so as to identify and mark invalid browsing records, thereby avoiding data interference caused by internal employee operation; second, the validity of the click behavior is distinguished according to a preset time threshold, thereby improving the real reference value of the click data; third, the collection behavior is marked for validity in combination with the matching condition of the resume basic information and the post hard requirements, which is helpful to more accurately evaluating the intention authenticity of the job seeker. Finally, the effective browsing data is obtained, which can objectively reflect the invitation efficiency and post attractiveness of the enterprise in the recruitment process, so that the post heat degrees of the recruitment posts calculated based on the effective browsing data are more accurate, thereby being beneficial to improving the comprehensive satisfaction of the employment recommendation system for recommending popular posts to the job seekers. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Fig. 1 This is an overall flow chart of the employment recommendation method based on big data of the present invention; Fig. 2 This is a schematic diagram of the principle of the big data-based employment recommendation system of the present invention; Fig. 3 This is a flow chart for determining the job matching degree between job seekers and various recruitment positions in the present invention. DETAILED DESCRIPTION

[0019] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] See also Figs. 1-3 The first embodiment of the present invention provides a method for job recommendation based on big data, comprising: S1: Collect basic resume information of several job seekers and recruitment information of several employing companies; and obtain historical browsing records and recruitment deadlines of recruitment positions posted by several employing companies on recruitment software platforms; S2: Determine the popularity of each job post based on historical browsing records; S3: Analyze the basic information of each job seeker's resume to obtain a resume classification set; S4: Analyze the recruitment information of each employing company to obtain a job classification set; S5: Determine the job matching degree between each job seeker and each recruitment position based on the resume classification set and the position classification set; S6: Generate a job recommendation sequence based on job matching, job popularity, and recruitment deadline.

[0021] In an embodiment of the present invention, determining the popularity of each recruitment position based on historical browsing records includes: Extract the historical browsing records of the job positions posted by each employing company on the recruitment software platform; the historical browsing records are composed of several job browsing records; Eliminate invalid data from historical browsing records to obtain valid browsing data; valid browsing data includes valid clicks, valid collections, and valid interview invitation rates; Obtain the probationary period resignation information for each recruitment position, and calculate the probationary period voluntary resignation rate for each recruitment position based on the probationary period resignation information; By formula Calculate the job heat GWRi of recruitment position i; where, is the effective click volume of recruitment position i, is the effective collection volume of recruitment position i, is the effective interview invitation rate for recruitment position i, is the voluntary turnover rate during the probation period of recruitment position i; a1, a2, a3, and a4 are all proportional coefficients greater than 0; i=1, 2,…, n, where n is the total number of employing companies.

[0022] For example, set the proportional coefficients a1=2, a2=2, a3=0.5, and a4=0.5; the effective click volume of recruitment position 1 =134, effective collection of recruitment position 1 =156, the effective interview invitation rate for recruitment position 1 =30%, the voluntary turnover rate during the probation period of recruitment position 1 =12%; calculated by the formula, the job popularity of recruitment position 1 is GWR1≈4.46.

[0023] It should be noted that the values ​​of the proportional coefficients a1, a2, a3, and a4 are related to the salary of the recruitment position; when the salary of the recruitment position is higher, the actual values ​​of the corresponding proportional coefficients a1 and a2 are set to be larger, and the actual values ​​of the proportional coefficients a3 and a4 are set to be smaller.

[0024] In an embodiment of the present invention, invalid data in the historical browsing records is removed, including: Obtain interview records for each job post and several job browsing records from historical browsing records; job browsing records include job seekers' browsing time, clicks, and favorites for the job post; interview records include the number of interview invitations and interview cancellations received from the employing company; Determine whether the job seeker is an employee of the employing company to which the recruitment position belongs; if yes, mark the corresponding position browsing record as invalid browsing record; if not, mark the corresponding position browsing record as valid browsing record; Determine whether the browsing time in the valid browsing record is greater than the preset time threshold; if yes, mark the click behavior of the corresponding job browsing record as a valid click; if not, mark the click behavior of the corresponding job browsing record as an invalid click; Determine whether the basic information of the job seeker's resume corresponding to the valid browsing record meets the hard requirements of the recruitment position; if yes, mark the collection behavior in the job browsing record as valid; if not, mark the collection behavior in the job browsing record as invalid; where hard requirements refer to the prerequisites that must be met for joining the recruitment position; The total number of valid clicks is marked as valid clicks, and the total number of valid collections is marked as valid collections; Calculate the effective interview invitation rate for each recruitment position based on the effective click volume and interview records.

[0025] For example, the hard requirements for recruitment position 2 are: educational requirement is "bachelor's degree or above", major requirement is "computer-related major", and working experience requirement is "3 years or more"; Set the preset duration threshold to 3 minutes; Job Applicant 1 is not currently employed by the company listed in Job Post 2. Job Applicant 1 browsed Job Post 2 for 5 minutes, clicked "Submitted", and saved the page as "Saved." The basic information of Job Applicant 1's resume is {Education = "Bachelor's Degree", Major = "Computer Science and Technology", Age = "25", Years of Work Experience = "4 Years", Skills = "Proficient in Back-End Development Technology", Certificate = "Software Examination Certificate"}; Since job seeker 1 is not currently employed by the company that employs the job, the corresponding job browsing record is marked as a valid browsing record; Since the browsing time of job seeker 1 in the valid browsing record is longer than the preset time threshold, the click behavior of job seeker 1 is marked as a valid click; Since the basic information of the resume of job seeker 1 in the valid browsing record meets the rigid requirements of recruitment position 2, the collection behavior of job seeker 1 in the position browsing record is marked as a valid collection.

[0026] The present invention improves the accuracy and practicality of recruitment data analysis by effectively eliminating invalid data in historical browsing records. First, by judging whether the job seeker is an employee of the employing enterprise to which the recruitment position belongs, invalid browsing records are identified and marked, thereby avoiding data interference caused by internal employee operations; secondly, the validity of click behaviors is distinguished according to a preset time threshold, thereby improving the real reference value of click data; thirdly, the validity of collection behaviors is marked in combination with the matching of basic resume information and rigid requirements of the position, which helps to more accurately evaluate the authenticity of the job seeker's intention. Finally, effective browsing data is obtained, which can objectively reflect the invitation efficiency and job attractiveness of the enterprise in the recruitment process, so that the subsequent calculation of the job popularity of the recruitment position based on the effective browsing data is more accurate, thereby helping to improve the overall satisfaction of the employment recommendation system in recommending popular positions to job seekers.

[0027] In an embodiment of the present invention, the effective interview invitation rate of each recruitment position is calculated based on the effective click volume and interview records, including: Extract the effective click volume and interview records of each recruitment position; Calculate the difference between the number of interview invitations and the number of interview cancellations in the interview records of each recruitment position to obtain the number of valid interview invitations for each recruitment position; Calculate the ratio of the number of effective interview invitations to the effective click volume for each recruitment position to obtain the effective interview invitation rate for each recruitment position.

[0028] For example, the number of valid clicks for Recruitment Position 2 is set to 74, the number of interview requests is set to 11, and the number of interview cancellations is set to 2; the number of interview requests is subtracted from the number of interview cancellations, and the number of valid interview invitations for Recruitment Position 2 is obtained to be 9 times; the ratio of the number of valid interview invitations for Recruitment Position 2 to the number of valid clicks is calculated, and the effective interview invitation rate for Recruitment Position 2 is obtained to be 12.16%.

[0029] In an embodiment of the present invention, the voluntary turnover rate during the probation period of each recruitment position is calculated based on the probation period turnover information, including: Obtain probationary period resignation data for each recruiting position posted by each employer within the most recent consecutive cycles. This probationary period resignation data includes the total number of employees who resigned and the type of resignation, including voluntary resignation and resignation due to incompetence. Calculate the ratio of the number of employees who voluntarily resigned from each recruitment position to the total number of employees who resigned, and obtain the voluntary turnover rate during the probation period of each recruitment position.

[0030] For example, assume that the number of employees who voluntarily resigned from recruitment position 3 is 4, and the total number of employees who resigned is 15; calculate the ratio of the number of employees who voluntarily resigned from recruitment position 3 to the total number of employees who resigned, and obtain the voluntary turnover rate of recruitment position 3 during the probation period as 26.67%.

[0031] In the embodiment of the present invention, the basic information of the resume of each job seeker is analyzed to obtain a resume classification set, including: Extract basic resume information of each job seeker; basic resume information includes intended position and personal information, and personal information includes education, major, age, years of work experience, skills information, and certification information; The basic information of several resumes with the same intended position is added into a resume sequence, and several resume sequences are integrated into a resume classification set.

[0032] In the embodiment of the present invention, the recruitment position information of each employing enterprise is analyzed to obtain a position classification set, including: Extract recruitment information from various employers; recruitment information includes job titles and hiring requirements, including educational requirements, major requirements, age requirements, years of work experience requirements, skills requirements, and certification requirements; Add several recruitment position information with the same position title into a recruitment position sequence, and integrate several recruitment position sequences into a position classification set.

[0033] In an embodiment of the present invention, determining the job matching degree between each job seeker and each recruitment position based on the resume classification set and the position classification set includes: Extracting a resume classification set and a position classification set; matching the intended positions of each job application resume sequence in the resume classification set with the position titles of each recruitment position sequence in the position classification set to obtain a matching result; wherein the matching result includes a matching success and a matching failure; If the matching result is successful, the job seeker's personal information will be matched with the recruitment requirements of the corresponding recruitment position to obtain several job matching scores; among which, the job matching scores include academic qualifications score, major score, age score, years of work experience score, skills score, and certificate score; Calculate the sum of the products of several job matching scores and corresponding weight coefficients to obtain the job matching degree; If the matching result is a match failure, the job matching degree between the corresponding job seeker and the corresponding recruitment position will be marked as 0.

[0034] It should be noted that the weight coefficients corresponding to the job matching scores are set by relevant experts based on experience, and the values ​​of each weight coefficient are related to the industry nature of the employing company; for example, financial companies attach great importance to accounting certificates, so the weight coefficient corresponding to the certificate score is set to be larger.

[0035] The present invention screens out combinations of job seekers and job positions that meet basic matching conditions through preliminary matching between resume classification sets and job classification sets, thereby improving matching efficiency and accuracy. On the basis of preliminary matching, a multi-dimensional matching score is further performed on the personal information of the job seekers and the job requirements, and a comprehensive job matching degree is calculated based on the weight coefficients of each scoring item, so that the matching result is more scientific and reasonable, and can more accurately reflect the degree of adaptation between the job seekers and the job positions. In addition, by directly marking the matching degree as 0 in the case of failed matching, the data processing process is simplified and the system operation efficiency is improved. This method not only helps employers to quickly screen out high-quality candidates, but also helps job seekers to accurately match suitable positions, thereby helping to improve the overall recruitment efficiency and satisfaction of the employment recommendation system.

[0036] In an embodiment of the present invention, a job position recommendation sequence is generated based on job matching degree, job popularity, and recruitment deadline, including: Extract the job matching degree between each job seeker and each recruitment position, the job popularity and recruitment deadline of each recruitment position posted by each employer; Determine whether the job matching degree is greater than a preset matching degree threshold; if yes, mark the corresponding recruitment position as a recommended position for the corresponding job seeker; if no, mark the corresponding recruitment position as an unmatched position for the corresponding job seeker; Integrate multiple positions to be recommended into a sequence of positions to be recommended; Sort the recommended job sequences in descending order of job matching degree to obtain the first recommended sequence; Sort the recommended job sequences in descending order of job popularity to obtain the second recommended sequence; Sort the recommended positions in ascending order of recruitment deadlines to obtain the third recommendation sequence; The first recommendation sequence, the second recommendation sequence and the third recommendation sequence are integrated into a job recommendation sequence.

[0037] For example, the job matching degree between job seeker 1 and job position 1 is set to 12, and the preset matching degree threshold is 10; since the job matching degree between job seeker 1 and job position 1 is greater than the preset matching degree threshold, job position 1 is marked as a job to be recommended for job seeker 1.

[0038] The present invention sets a matching threshold to screen out recommended positions that meet the job seeker's abilities and career intentions, ensuring the relevance and effectiveness of the recommended content; then, it sorts positions in multiple dimensions based on job matching from high to low, job popularity from high to low, and recruitment deadlines from near to far, forming multiple recommendation sequences, thereby taking into account the quality of job matching, job competition intensity, and timeliness requirements. Finally, multiple recommendation sequences are integrated to generate a comprehensive job recommendation sequence, which improves the scientific nature and practicality of the recommendation results. This method not only helps job seekers efficiently obtain high-quality job information, but also helps employers reach potential candidates with higher matching degrees more quickly, optimizes recruitment resource allocation, and improves the overall operating efficiency and service quality of the employment service platform.

[0039] The second embodiment of the present invention provides an employment recommendation system based on big data, comprising: a data processing module, and a data collection module and an employment recommendation module connected thereto; Data collection module: used to collect basic resume information of several job seekers and recruitment information of several employers; as well as to obtain the historical browsing records and recruitment deadlines of recruitment positions posted by several employers on the recruitment software platform; Data processing module: used to determine the popularity of each recruitment position based on historical browsing records; analyze the basic information of each job seeker's resume to obtain a resume classification set; analyze the recruitment position information of each employing company to obtain a position classification set; Employment recommendation module: used to determine the job matching degree between each job seeker and each recruitment position based on the resume classification set and the position classification set; generate a job recommendation sequence based on the job matching degree, job popularity, and recruitment deadline.

[0040] Some of the data in the above formula are calculated by removing the dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0041] Working principle of the present invention: The present invention collects basic resume information of several job seekers and recruitment position information of several employing companies; and obtains historical browsing records and recruitment deadlines of recruitment positions published by several employing companies on a recruitment software platform; determines the job popularity of each recruitment position based on the historical browsing records; analyzes the basic resume information of each job seeker to obtain a resume classification set; analyzes the recruitment position information of each employing company to obtain a position classification set; determines the job matching degree between each job seeker and each recruitment position based on the resume classification set and the position classification set; and generates a job position recommendation sequence based on the job matching degree, job popularity, and recruitment deadline.

[0042] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for job recommendation based on big data, characterized in that: include: Collect basic resume information of several job seekers and recruitment information of several employing companies; Also, obtain the historical browsing records and recruitment deadlines of several employers’ job positions posted on recruitment software platforms; Determine the popularity of each job post based on historical browsing records; Analyze the basic information of each job seeker's resume to obtain a resume classification set; Analyze the recruitment information of each employing company to obtain a set of job classifications; Determine the job matching degree between each job seeker and each recruitment position based on the resume classification set and the position classification set; Generate a job recommendation sequence based on job matching, job popularity, and recruitment deadline.

2. The employment recommendation method based on big data according to claim 1, characterized in that: Determining the popularity of each recruitment position based on historical browsing records includes: Extract the historical browsing records of the job positions posted by each employing company on the recruitment software platform; the historical browsing records are composed of several job browsing records; Eliminate invalid data from historical browsing records to obtain valid browsing data; valid browsing data includes valid clicks, valid collections, and valid interview invitation rates; Obtain the probationary period resignation information for each recruitment position, and calculate the probationary period voluntary resignation rate for each recruitment position based on the probationary period resignation information; By formula Calculate the job heat GWRi of recruitment position i; where, is the effective click volume of recruitment position i, is the effective collection volume of recruitment position i, is the effective interview invitation rate for recruitment position i, is the voluntary turnover rate during the probation period of recruitment position i; a1, a2, a3, and a4 are all proportional coefficients greater than 0; i=1, 2,…, n, where n is the total number of employing companies.

3. The employment recommendation method based on big data according to claim 2, characterized in that: The step of removing invalid data from the historical browsing records includes: Obtain interview records for each job post and several job browsing records from historical browsing records; job browsing records include job seekers' browsing time, clicks, and favorites for the job post; interview records include the number of interview invitations and interview cancellations received from the employing company; Determine whether the job seeker is an employee of the employing company to which the recruitment position belongs; if yes, mark the corresponding position browsing record as invalid browsing record; if not, mark the corresponding position browsing record as valid browsing record; Determine whether the browsing time in the valid browsing record is greater than the preset time threshold; if yes, mark the click behavior of the corresponding job browsing record as a valid click; if not, mark the click behavior of the corresponding job browsing record as an invalid click; Determine whether the basic information of the job seeker's resume corresponding to the valid browsing record meets the hard requirements of the recruitment position; if yes, mark the collection behavior in the job browsing record as valid; if not, mark the collection behavior in the job browsing record as invalid; where hard requirements refer to the prerequisites that must be met for joining the recruitment position; The total number of valid clicks is marked as valid clicks, and the total number of valid collections is marked as valid collections; Calculate the effective interview invitation rate for each recruitment position based on the effective click volume and interview records.

4. The employment recommendation method based on big data according to claim 3, characterized in that: The calculation of the effective interview invitation rate for each recruitment position based on effective clicks and interview records includes: Extract the effective click volume and interview records of each recruitment position; Calculate the difference between the number of interview invitations and the number of interview cancellations in the interview records of each recruitment position to obtain the number of valid interview invitations for each recruitment position; Calculate the ratio of the number of effective interview invitations to the effective click volume for each recruitment position to obtain the effective interview invitation rate for each recruitment position.

5. The employment recommendation method based on big data according to claim 2, characterized in that: The calculation of the probationary period voluntary turnover rate of each recruitment position based on the probationary period resignation information includes: Obtain probationary period resignation data for each employer's job postings over the most recent consecutive periods. This probationary period resignation data includes the total number of employees who resigned and the type of resignation, including voluntary resignation and resignation due to incompetence. Calculate the ratio of the number of employees who voluntarily resigned from each recruitment position to the total number of employees who resigned, and obtain the voluntary turnover rate during the probation period of each recruitment position.

6. The employment recommendation method based on big data according to claim 1, characterized in that: The basic information of each job seeker's resume is analyzed to obtain a resume classification set, including: Extract basic resume information of each job seeker; basic resume information includes intended position and personal information, and personal information includes education, major, age, years of work experience, skills information, and certification information; The basic information of several resumes with the same intended position is added into a resume sequence, and several resume sequences are integrated into a resume classification set.

7. The employment recommendation method based on big data according to claim 1, characterized in that: The recruitment information of each employing enterprise is analyzed to obtain a set of job classifications, including: Extract recruitment information from various employers; recruitment information includes job titles and hiring requirements, including educational requirements, major requirements, age requirements, years of work experience requirements, skills requirements, and certification requirements; Add several recruitment position information with the same position title into a recruitment position sequence, and integrate several recruitment position sequences into a position classification set.

8. The employment recommendation method based on big data according to claim 1, characterized in that: The determination of the job matching degree between each job seeker and each recruitment position based on the resume classification set and the position classification set includes: Extracting a resume classification set and a position classification set; matching the intended positions of each job application resume sequence in the resume classification set with the position titles of each recruitment position sequence in the position classification set to obtain a matching result; wherein the matching result includes a matching success and a matching failure; If the matching result is successful, the job seeker's personal information will be matched with the recruitment requirements of the corresponding recruitment position to obtain several job matching scores; among which, the job matching scores include academic qualifications score, major score, age score, years of work experience score, skills score, and certificate score; Calculate the sum of the products of several job matching scores and corresponding weight coefficients to obtain the job matching degree; If the matching result is a match failure, the job matching degree between the corresponding job seeker and the corresponding recruitment position will be marked as 0.

9. The employment recommendation method based on big data according to claim 1, characterized in that: The generation of a job recommendation sequence based on job matching degree, job popularity, and recruitment deadline includes: Extract the job matching degree between each job seeker and each recruitment position, the job popularity and recruitment deadline of each recruitment position posted by each employer; Determine whether the job matching degree is greater than a preset matching degree threshold; if yes, mark the corresponding recruitment position as a recommended position for the corresponding job seeker; if no, mark the corresponding recruitment position as an unmatched position for the corresponding job seeker; Integrate multiple positions to be recommended into a sequence of positions to be recommended; Sort the recommended job sequences in descending order of job matching degree to obtain the first recommended sequence; Sort the recommended job sequences in descending order of job popularity to obtain the second recommended sequence; Sort the recommended positions in ascending order of recruitment deadlines to obtain the third recommendation sequence; The first recommendation sequence, the second recommendation sequence and the third recommendation sequence are integrated into a job recommendation sequence.

10. A big data-based employment recommendation system, used to implement the big data-based employment recommendation method according to any one of claims 1 to 9, characterized in that: include: Data processing module, and the data collection module and employment recommendation module connected thereto; The data collection module is used to collect basic resume information of several job seekers and recruitment information of several employing companies; Also, obtain the historical browsing records and recruitment deadlines of several employers’ job positions posted on recruitment software platforms; The data processing module is used to determine the popularity of each recruitment position based on historical browsing records; analyze the basic information of each job seeker's resume to obtain a resume classification set; Analyze the recruitment information of each employing company to obtain a set of job classifications; The employment recommendation module is used to determine the job matching degree between each job seeker and each recruitment position based on the resume classification set and the position classification set; Generate a job recommendation sequence based on job matching, job popularity, and recruitment deadline.

Images