An Internet of Things-based electronic recruitment matching method and system

Abstract

This invention discloses an electronic recruitment matching method and system based on the Internet of Things (IoT), belonging to the field of electronic recruitment technology. When a target company is recruiting, the invention analyzes the quality of its recruitment. If the recruitment quality is low, it provides upgrade services. Then, in subsequent recruitment processes, if a target job seeker matches the target company, the invention increases the frequency of the target company's recommendations among job seekers based on the matching situation between the job seeker and competing companies. This provides the target company with targeted recommendation schemes among job seekers, increasing its exposure, competitiveness, and attractiveness, thereby increasing the company's chances of being prioritized for recruitment. This provides a foundation for recruiting high-quality job seekers, ensuring the quality of recruitment and reducing the probability of competing companies recruiting high-quality job seekers, ultimately contributing to improving the company's overall strength.

Description

Technical Field

[0001] This invention relates to the field of electronic recruitment technology, and specifically to an electronic recruitment matching method and system based on the Internet of Things. Background Technology

[0002] In online recruitment, companies often receive a large number of resumes from job seekers and then screen them. Electronic recruitment matching methods can quickly filter resumes that meet basic requirements, significantly saving time and effort compared to manual screening. For job seekers, these methods can accurately recommend multiple suitable positions based on their resume information and job preferences, enabling them to find suitable job opportunities more quickly and improving job search efficiency.

[0003] Existing technologies, such as the invention patent application CN109558429B, disclose a two-way recommendation method for talent services based on internet big data. This method comprises three main parts: a data access module, a data matching and computing cluster, and a data distribution module. Specifically, the data access module includes a job seeker / recruitment behavior database and a resume / job business database; the data matching and computing cluster includes an active user cache, a data text analysis result cache, a job seeker matching calculator, and a job matching calculator; and the data distribution module includes a result database. The specific implementation steps are: first, data understanding; second, data cleaning; third, feature selection and evaluation; fourth, calculation and storage; fifth, recommendation; and sixth, incremental and updated data. This invention, by capturing user behavior and collecting talent and job information in real time, achieves real-time and accurate matching of massive amounts of resume and job data, and can recommend jobs that better match job seekers' preferences, greatly improving service efficiency.

[0004] Existing technologies, such as the invention patent application with publication number CN115934899A, disclose a method, apparatus, electronic device, and storage medium for recommending resumes in the IT industry. The method includes: acquiring and preprocessing company recruitment texts and multiple job seeker resume texts; dividing the preprocessed company recruitment texts and job seeker resume texts into multiple different text blocks, and assigning corresponding recruitment preference weighting values ​​to different text blocks according to recruitment requirements; calculating the matching degree between each text block of the company recruitment text and the corresponding text block of the job seeker resume text; multiplying the matching degree of each text block by the corresponding recruitment preference weighting value and summing them to obtain the similarity of multiple company recruitment texts and job seeker resume texts; sorting them in descending order of similarity; and selecting the job seeker resume text with the highest ranking as the recommended resume. This invention solves the problem of personalized resume recommendation in the IT industry, achieving efficient and accurate matching of resumes and job postings, and improving the work efficiency of corporate recruiters.

[0005] Existing technology, such as the invention patent application with publication number CN114943517A, discloses an IoT-based electronic recruitment matching method, system, and storage medium. S1: Obtain preliminary resume information for target positions on a job recruitment platform; S2: Extract the first, second, third, and fourth fields from the preliminary resume information; wherein the first field is the job seeker's identity information, the second field is the job seeker's educational background information, the third field is the job seeker's work experience information, and the fourth field is a brief introduction to the job seeker's work skills; S3: Match and filter the preliminary resume information using a pre-set model of valid resume information, determining that preliminary resume information where none of the first, second, third, and fourth fields are blank is valid resume information; S4: Parse the valid resume information and sort it according to the number of characters in each field; S5: Push all valid resumes in order according to the sorting results.

[0006] The above solutions have at least the following shortcomings: 1. When job seekers are looking for jobs, they may be matched with multiple companies, and there is competition among these companies. Increasing the company's exposure to job seekers helps to deepen the company's impression on job seekers, thereby increasing the probability of successful recruitment. However, the above solutions lack analysis on how to improve the company's competitiveness and increase the company's recruitment success rate when there is competition among multiple companies. Therefore, they cannot increase the company's competitiveness during recruitment, cannot attract high-quality job seekers, and reduce the effectiveness of recruitment.

[0007] 2. The compatibility between job seekers and different companies varies. Therefore, providing targeted and personalized recommendation services to companies based on their compatibility can increase their exposure and competitiveness among job seekers. However, the above solution only analyzes the matching degree between companies and job seekers and does not set up a recommendation scheme for companies among job seekers. This fails to improve the competitiveness of companies among job seekers, thus failing to increase the probability of companies being given priority in recruitment, reducing the effectiveness of recruiting high-quality job seekers, and increasing recruitment time costs. Summary of the Invention

[0008] In view of the above-mentioned technical deficiencies, the purpose of this invention is to provide an electronic recruitment matching method and system based on the Internet of Things.

[0009] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: In the first aspect, the present invention provides an electronic recruitment matching method based on the Internet of Things, including the following steps: S1, Recruitment data acquisition: acquiring recruitment description data, prospective job seeker data and suitable job seeker data of recruitment positions of target companies, and acquiring recruitment description data, prospective job seeker data and suitable job seeker data of recruitment positions of competing companies.

[0010] S2. Recruitment Data Analysis: Utilize the recruitment description data, prospective job seeker data, and suitable job seeker data of the target company's job postings, as well as the recruitment description data and prospective job seeker data of the competing companies' job postings, to analyze the recruitment quality of the target company's job postings. Recruitment quality includes high quality and low quality. When the recruitment quality of the target company's job postings is low, proceed to S3.

[0011] S3. Recruitment Upgrade Analysis: Obtain the job posting data of the target company, analyze the recruitment needs of the target company's job postings, including high demand and general demand, and at the same time obtain the upgrade services and posting data of the job postings of each competitor company. Select the target upgrade service for the target company's job postings and display and upgrade prompts. If the target company selects the upgrade, when the target job seeker applies for the job, execute S4.

[0012] S4. Job Matching: When a target job seeker applies for a job, the system obtains the job seeker's resume data and analyzes the match between the job seeker and the target company. If the match is successful, the system sets the target company's recommendation data for the job seeker based on the target company's upgraded services. If the match is unsuccessful, no settings are made.

[0013] Secondly, the present invention provides an Internet of Things-based electronic recruitment matching system, comprising: a recruitment data acquisition module, used to acquire recruitment description data, prospective job seeker data and suitable job seeker data of recruitment positions of target companies, and to acquire recruitment description data, prospective job seeker data and suitable job seeker data of recruitment positions of competing companies.

[0014] The recruitment data analysis module is used to analyze the recruitment quality of the target company's job postings by utilizing the job description data, prospective job seeker data, and suitable job seeker data of the target company's job postings, as well as the job description data and prospective job seeker data of the competing companies' job postings. The recruitment quality is divided into high quality and low quality. When the recruitment quality of the target company's job postings is low, the recruitment upgrade analysis module is executed.

[0015] The recruitment upgrade analysis module is used to obtain the job posting data of target companies, analyze the recruitment needs of target companies' job postings, including high demand and general demand, and obtain the upgrade services and posting data of job postings of various competing companies. It selects target upgrade services for the job postings of the target company, displays and prompts upgrades, and if the target company selects an upgrade, the recruitment matching module is executed when the target job seeker applies for a job.

[0016] The recruitment matching module is used to obtain the resume data of target job seekers when they apply for jobs, analyze the matching situation between target job seekers and target companies, and if the matching situation is a match, set the target company's recommendation data on the target job seeker's side based on the target company's upgraded services. If the matching situation is a mismatch, no settings are made.

[0017] The beneficial effects of this invention are as follows: This invention provides an electronic recruitment matching method and system based on the Internet of Things. When a target company is recruiting, the quality of its recruitment is analyzed. If the quality of the recruitment is low, upgrade services are provided to the target company. Then, in subsequent recruitment, if a target job seeker matches the target company, the frequency of the target company's recommendations among job seekers is increased based on the matching situation between the job seeker and competing companies. This provides the target company with targeted recommendation solutions among job seekers, increases the target company's exposure among job seekers, enhances the target company's competitiveness and attractiveness, thereby increasing the probability of the company being given priority in recruitment. This provides a foundation for the company to recruit high-quality job seekers, ensures the quality of the company's recruitment, and reduces the probability of competing companies recruiting high-quality job seekers, thus helping to improve the company's overall strength. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the implementation steps of the method of the present invention.

[0020] Figure 2 This is a schematic diagram of the system structure connection of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Example 1:

[0023] Please see Figure 1As shown, an electronic recruitment matching method based on the Internet of Things includes the following steps: S1, Recruitment data acquisition: Acquire recruitment description data, prospective job seeker data, and suitable job seeker data of the target company's recruitment positions, and acquire recruitment description data, prospective job seeker data, and suitable job seeker data of the recruitment positions of each competing company.

[0024] It should be noted that the recruitment information includes job descriptions, requirements, and benefits; prospective job seekers are those who believe they are a good fit for the job, i.e., those who actively communicate with the recruiting HR; and suitable job seekers are those who are a good match between the job seeker on the recruitment platform and the company's job posting, i.e., those who actively communicate with the recruiting HR.

[0025] The recruitment platform uses job seekers' resumes and job requirements in company recruitment positions to analyze the suitability between job seekers and company recruitment positions. When a match is found, the job seeker will be given priority to the recruiting personnel, who will then proactively communicate with them. For details on the analysis of the suitability between job seekers and company recruitment positions, please refer to the invention patent with publication number CN118798836A, entitled "Precise Matching Recruitment System Based on Big Data Analysis," which will not be elaborated here.

[0026] The data on potential job seekers includes their resumes and click frequency. The resume data refers to the content of their resumes. Click frequency refers to the number of times they clicked on the main interface of the job posting.

[0027] The data on suitable job seekers includes the resume content of each suitable job seeker.

[0028] S2. Recruitment Data Analysis: Utilize the recruitment description data, prospective job seeker data, and suitable job seeker data of the target company's job postings, as well as the recruitment description data and prospective job seeker data of the competing companies' job postings, to analyze the recruitment quality of the target company's job postings. Recruitment quality includes high quality and low quality. When the recruitment quality of the target company's job postings is low, proceed to S3.

[0029] In a specific embodiment, the process of analyzing the recruitment quality of the target company's job postings is as follows: Resume data of each prospective job seeker is obtained from the prospective job seeker data of the target company's job postings; scores are calculated for each prospective job seeker using the job description data of the target company's job postings; scores are obtained for each prospective job seeker in the target company's job postings; suitable job seekers are obtained from the suitable job seeker data of the target company's job postings; each prospective job seeker is compared with each suitable job seeker; and prospective job seekers who are identical to each suitable job seeker, along with each suitable job seeker, are considered high-quality job seekers in the target company's job postings.

[0030] It should be noted that the scores of each prospective job seeker in the target company's job postings represent the matching coefficient between the job postings and the prospective job seekers. The specific calculation method is the same as that used in the invention patent with publication number CN118798836A, entitled "Precise Matching Recruitment System Based on Big Data Analysis," which calculates the matching coefficient between the resumes to be matched and the target job postings. Therefore, it will not be repeated here.

[0031] Simultaneously, resume data of potential job seekers is obtained from the recruitment data of various competing companies. According to the calculation method of the score of each potential job seeker in the recruitment positions of the target company, the score of each potential job seeker in the recruitment positions of various competing companies is calculated, and the high-quality job seekers in the recruitment positions of various competing companies are also obtained.

[0032] Input the scores of each prospective job seeker and the number of high-quality job seekers for each job opening at the target company, as well as the scores of each prospective job seeker and the number of high-quality job seekers for each job opening at each competing company, into the quality assessment model, and output the recruitment quality assessment results for the target company's job openings.

[0033] The recruitment quality assessment results include values ​​of 1 and 0. A recruitment quality assessment result of 1 indicates that the recruitment quality of the target company's recruitment positions is high, while a recruitment quality assessment result of 0 indicates that the recruitment quality of the target company's recruitment positions is low.

[0034] The expression for the quality assessment model described above is:

[0035] Where γ represents the recruitment quality assessment result of the target company's job posting, FZ represents the average score of each prospective job seeker for the target company's job posting, κ is the ratio of the number of high-quality job seekers to the number of suitable job seekers for the target company's job posting, and FZ is the ratio of FZ to FZ. j κ represents the average score of all prospective job seekers for the position offered by the j-th competing company. j Let ε be the ratio of the number of high-quality job seekers to the number of suitable job seekers in the job postings of the j-th competing company, where j represents the number of each competing company, j is a positive integer, J represents the number of competing companies, and ε is a preset recruitment quality assessment threshold.

[0036] It should be noted that the preset recruitment quality assessment threshold is a critical value for judging whether the recruitment quality is high. It is set by the staff of the recruitment platform. When it is greater than or equal to the recruitment quality assessment threshold, it indicates that the recruitment quality is high, and vice versa.

[0037] in, The calculation result is the recruitment quality assessment value for the target company's recruitment positions.

[0038] S3. Recruitment Upgrade Analysis: Obtain the job posting data of the target company, analyze the recruitment needs of the target company's job postings, including high demand and general demand, and at the same time obtain the upgrade services and posting data of the job postings of each competitor company. Select the target upgrade service for the target company's job postings and display and upgrade prompts. If the target company selects the upgrade, when the target job seeker applies for the job, execute S4.

[0039] This involves obtaining job posting data from the recruitment platform's backend, including the posting time, closing time, number of openings, and daily online recruitment duration for each job posting.

[0040] In a specific embodiment, the process of analyzing the recruitment needs of the target company's job postings is as follows: S31, obtain the posting time, closing time, number of recruits, and daily online recruitment duration from the job posting data of the target company; obtain the duration of each recruitment for the target company's job postings based on the posting and closing times of each recruitment for the target company's job postings; and obtain the recruitment frequency of the target company's job postings based on the posting time of each recruitment for the target company's job postings.

[0041] S32. Obtain the recruitment frequency, duration of each recruitment, number of recruits, and daily online recruitment duration of each competitor's recruitment positions from the recruitment platform. Then, calculate the average of each of these averages and use them as reference recruitment frequency, reference recruitment duration, reference number of recruits, and reference daily online recruitment duration, respectively, and denoted as f, T1, R, and T2.

[0042] S33, Expression for the Recruitment Demand Assessment Model:

[0043] In the formula, μ represents the assessment result of the recruitment demand for the target company's job posting, e represents the natural constant, f′ represents the recruitment frequency of the target company's job posting, and T1′ represents the recruitment frequency of the target company's job posting. c R c ′、T2′ c These represent the duration, number of openings, and daily online recruitment duration for the target company's job postings in the c-th recruitment round, respectively. c represents the recruitment round number, c is a positive integer, and C represents the total number of recruitment rounds. This is the preset threshold for assessing recruitment needs.

[0044] μ = 1 indicates that the recruitment demand for the target company's job is high, while μ = -1 indicates that the recruitment demand for the target company's job is average.

[0045] It should be noted that the preset recruitment demand assessment threshold is a critical value for judging whether the recruitment demand is high. It is set by the staff of the recruitment platform. When it is greater than or equal to the preset recruitment demand assessment threshold, it indicates that the recruitment demand is high, and otherwise it is a general demand.

[0046] The recruitment platform offers various upgrade services for companies with different needs. Each upgrade service has different validity periods, permissions, and promotion volume. Users can choose to upgrade their accounts to improve recruitment quality when the quality of their recruitment is low.

[0047] In another specific embodiment, the process of selecting target upgrade services for the recruitment positions of the target enterprise is as follows: obtain each initial upgrade service corresponding to high demand from the recruitment platform, and obtain the recruitment quality assessment value, recruitment attraction value, recruitment effect value and recruitment attraction value of each upgrading enterprise in each initial upgrade service and each competing enterprise.

[0048] It should be noted that the recruitment effectiveness value is the recruitment quality assessment value after the service upgrade minus the recruitment quality assessment value before the service upgrade, and then divided by the recruitment quality assessment value before the service upgrade.

[0049] Using the job posting data of the target company, the job posting data of each competitor, and the upgrade services, we calculate the recruitment attractiveness value of the target company and the recruitment attractiveness value of each competitor, and extract the recruitment quality assessment value of the target company's job postings. Then, we calculate the fit value between each initial upgrade service and the target company, and select the initial upgrade service with the largest fit value as the target upgrade service.

[0050] In the above, the calculation of the recruitment attractiveness value of the target company is specifically as follows: The click frequency of each potential job seeker for each job posting in the target company is obtained from the data of potential job seekers for the target company's job openings, denoted as PZ. p We obtain the click frequency of each prospective job seeker for each job posting from the data of prospective job seekers for each competitor's job posting, denoted as PZ. jp Simultaneously, the scores of each prospective job seeker for the target company's job postings and the scores of each prospective job seeker for the job postings of each competing company are obtained and denoted as FZ respectively. p and FZ jp j represents the ID of each competing company, which is a positive integer, and p represents the ID of each prospective job seeker, which is a positive integer.

[0051] Using the calculation formula: The recruitment attractiveness value χ of the target company is obtained, where J represents the number of competing companies, P represents the number of prospective job seekers, and e represents the natural constant.

[0052] It should be noted that the recruitment attractiveness value of each competing company is calculated in the same way as that of the target company.

[0053] Preferably, the process for calculating the compatibility value between each initial upgrade service and the target enterprise is as follows: divide the recruitment attraction value of each upgraded enterprise in each initial upgrade service by the average recruitment attraction value of each competing enterprise to obtain the recruitment attraction value of each upgraded enterprise in each initial upgrade service, denoted as χ. qy , where q represents the number of each initial upgrade service, y represents the number of each upgrade enterprise, and q and y are positive integers;

[0054] Simultaneously, the recruitment quality assessment value and recruitment effectiveness value of each upgraded enterprise in each initial upgrade service are respectively denoted as ε. qy and σ qy And the recruitment quality assessment value of the target company's recruitment position is denoted as ε′, and then the calculation formula is used: The compatibility value φ between the q-th initial upgrade service and the target enterprise is obtained. q In the formula, Y and Q represent the number of upgraded enterprises and the number of initial upgrade services, respectively.

[0055] S4. Job Matching: When a target job seeker applies for a job, the system obtains the job seeker's resume data and analyzes the match between the job seeker and the target company. If the match is successful, the system sets the target company's recommendation data for the job seeker based on the target company's upgraded services. If the match is unsuccessful, no settings are made.

[0056] The above analysis of the matching between target job seekers and target companies refers to the analysis of the suitability between the target job seeker's resume and the target company's job posting. The specific analysis method is the same as the method for determining whether the person-job match is consistent in the invention patent with publication number CN118798836A, entitled "Precise Matching Recruitment System Based on Big Data Analysis". It will not be repeated here.

[0057] In a specific embodiment, the process of setting the target company's recommendation data for the target job seeker is as follows: using the job description data of the target company's recruitment position and the resume data of the target job seeker, the target job seeker's score in the target company is obtained. Similarly, the target job seeker's score in each competing company is obtained. Then, the initial competition level of the target company and each competing company in the target job seeker's field is analyzed, where the initial competition level is level one, level two, and level three.

[0058] Preferably, the initial competition level analysis process of the target company among target job seekers is as follows: The score of the target job seeker in the target company is taken as the target score. The number of potential job seekers and suitable job seekers with the target score at the time of recruitment are obtained from the backend of the recruitment platform. The sum is used to obtain the number of marked job seekers. At the same time, the number of employees with the target score at the time of recruitment is obtained from the backend of the recruitment platform. The number of employees with the target score at the time of recruitment is divided by the number of marked job seekers to obtain the employment ratio of the target company. Similarly, the employment ratio of each competing company is obtained.

[0059] Select the largest and smallest hiring ratios from the target company's hiring ratio and the hiring ratios of each competitor's company. Then, add the largest and smallest hiring ratios together and divide by 2 to get the median hiring ratio. At the same time, select the mode from the hiring ratios of the target company and the hiring ratios of each competitor's company as the mode hiring ratio. Then, sort the largest, smallest, median, and mode hiring ratios in descending order and label them as the first hiring ratio, the second hiring ratio, the third hiring ratio, and the fourth hiring ratio, respectively.

[0060] Among them, the range between the first and second recruitment ratios corresponds to the recruitment ratio range of level one in the initial competition level, the range between the second and third recruitment ratios corresponds to the recruitment ratio range of level two in the initial competition level, and the range between the third and fourth recruitment ratios corresponds to the recruitment ratio range of level three in the initial competition level. Then, based on the recruitment ratio of the target company, the initial competition level of the target company among the target job seekers is obtained.

[0061] If the target company's initial competition level among target job seekers is Level 1, obtain all competing companies with an initial competition level of Level 1 among target job seekers as labeled companies. Obtain the average recommendation frequency of each labeled company among job seekers from the recruitment platform's backend. Then, select the highest average recommendation frequency as the reference recommendation frequency. Extract the recruitment attraction value of the target company and the recruitment attraction values ​​of each labeled company. If the recruitment attraction value of the target company is greater than the recruitment attraction values ​​of all labeled companies, set the recommendation frequency of the target company among target job seekers to be 1.2 times the reference recommendation frequency. If the recruitment attraction value of the target company is less than the recruitment attraction value of at least one labeled company, set the recommendation frequency of the target company among target job seekers to be 1.5 times the reference recommendation frequency.

[0062] If the initial competitive level of the target company among the target job seekers is level two, the recommendation frequency of the target company among the target job seekers is set to 1.8 times the reference recommendation frequency.

[0063] If the initial competition level of the target company among the target job seekers is level three, the recommendation frequency of the target company among the target job seekers is set to twice the reference recommendation frequency. This is used to obtain the recommendation frequency of the target company among the target job seekers as recommendation data.

[0064] Example 2:

[0065] Please see Figure 2 As shown, an Internet of Things-based electronic recruitment matching system includes: a recruitment data acquisition module, a recruitment data analysis module, a recruitment upgrade analysis module, and a recruitment matching module.

[0066] The recruitment data acquisition module is used to acquire recruitment description data, prospective job seeker data, and suitable job seeker data for the target company's job postings, as well as recruitment description data, prospective job seeker data, and suitable job seeker data for the job postings of competing companies.

[0067] The recruitment data analysis module is used to analyze the recruitment quality of the target company's job postings by utilizing the job description data, prospective job seeker data, and suitable job seeker data of the target company's job postings, as well as the job description data and prospective job seeker data of the competing companies' job postings. The recruitment quality is divided into high quality and low quality. When the recruitment quality of the target company's job postings is low, the recruitment upgrade analysis module is executed.

[0068] The recruitment upgrade analysis module is used to obtain the job posting data of target companies, analyze the recruitment needs of target companies' job postings, including high demand and general demand, and obtain the upgrade services and posting data of job postings of various competing companies. It selects target upgrade services for the job postings of the target company, displays and prompts upgrades, and if the target company selects an upgrade, the recruitment matching module is executed when the target job seeker applies for a job.

[0069] The recruitment matching module is used to obtain the resume data of target job seekers when they apply for jobs, analyze the matching situation between target job seekers and target companies, and if the matching situation is a match, set the target company's recommendation data on the target job seeker's side based on the target company's upgraded services. If the matching situation is a mismatch, no settings are made.

[0070] This invention analyzes the recruitment quality of a target company when it is recruiting. If the recruitment quality is low, it provides upgrade services. Then, in subsequent recruitment processes, if a job seeker matches the target company, it increases the frequency of the target company's recommendations among job seekers based on the matching situation between the job seeker and competing companies. This provides the target company with targeted recommendation strategies among job seekers, increasing its exposure, competitiveness, and attractiveness, thereby increasing the company's chances of being prioritized for recruitment. This provides a foundation for recruiting high-quality job seekers, ensuring the quality of recruitment and reducing the probability of competing companies recruiting high-quality job seekers, ultimately improving the company's overall strength.

[0071] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. An electronic recruitment matching method based on the Internet of Things, characterized in that, Includes the following steps: S1. Recruitment Data Acquisition: Acquire recruitment information, prospective job seekers, and suitable job seekers for the target company's job postings, and acquire recruitment information, prospective job seekers, and suitable job seekers for the job postings of competing companies. S2. Recruitment Data Analysis: Utilize the recruitment description data, prospective job seeker data, and suitable job seeker data of the target company's recruitment positions, as well as the recruitment description data and prospective job seeker data of the recruitment positions of various competing companies, to analyze the recruitment quality of the target company's recruitment positions. Recruitment quality includes high quality and low quality. When the recruitment quality of the target company's recruitment positions is low, proceed to S3. S3. Recruitment Upgrade Analysis: Obtain the job posting data of the target company, analyze the recruitment needs of the target company's job postings, including high demand and general demand, and at the same time obtain the upgrade services and posting data of the job postings of each competitor company. Select the target upgrade service for the target company's job postings and display and upgrade prompts. If the target company selects the upgrade, when the target job seeker applies for the job, execute S4. S4. Job Matching: When a target job seeker applies for a job, the system obtains the job seeker's resume data and analyzes the match between the job seeker and the target company. If the match is successful, the system sets the target company's recommendation data for the job seeker based on the target company's upgraded services. If the match is unsuccessful, no settings are made.

2. The electronic recruitment matching method based on the Internet of Things according to claim 1, characterized in that, The specific process for analyzing the recruitment quality of the target company's job postings is as follows: The resume data of each prospective job seeker is obtained from the prospective job seeker data of the target company’s job postings. The job description data of the target company’s job postings is used to calculate the score of each prospective job seeker. The score of each prospective job seeker in the target company’s job postings is obtained from the suitable job seeker data of the target company’s job postings. Each prospective job seeker is compared with each suitable job seeker. The prospective job seekers who are the same as each suitable job seeker, as well as each suitable job seeker, are identified as high-quality job seekers in the target company’s job postings. At the same time, we obtain the resume data of each prospective job seeker from the recruitment positions of each competing company, calculate the score of each prospective job seeker in the recruitment positions of each competing company according to the calculation method of each prospective job seeker in the recruitment positions of the target company, and obtain the high-quality job seekers in the recruitment positions of each competing company. Input the scores of each prospective job seeker and the number of high-quality job seekers for each job opening in the target company, as well as the scores of each prospective job seeker and the number of high-quality job seekers for each job opening in each competing company, into the quality assessment model, and output the recruitment quality assessment results for the job openings of the target company. The recruitment quality assessment results include values ​​of 1 and 0. A recruitment quality assessment result of 1 indicates that the recruitment quality of the target company's recruitment positions is high, while a recruitment quality assessment result of 0 indicates that the recruitment quality of the target company's recruitment positions is low.

3. The electronic recruitment matching method based on the Internet of Things according to claim 2, characterized in that, The expression for the quality assessment model is: Where γ represents the recruitment quality assessment result of the target company's job posting, FZ represents the average score of each prospective job seeker for the target company's job posting, κ is the ratio of the number of high-quality job seekers to the number of suitable job seekers for the target company's job posting, and FZ is the ratio of FZ to FZ. j κ represents the average score of all prospective job seekers for the position offered by the j-th competing company. j Let ε be the ratio of the number of high-quality job seekers to the number of suitable job seekers in the job postings of the j-th competing company, where j represents the number of each competing company, j is a positive integer, J represents the number of competing companies, and ε is a preset recruitment quality assessment threshold.

4. The electronic recruitment matching method based on the Internet of Things according to claim 1, characterized in that, The specific process for analyzing the recruitment needs of the target company's job openings is as follows: S31. Obtain the posting time, closing time, number of recruits, and daily online recruitment duration for each job posting from the target company's job posting data; obtain the duration of each job posting for the target company based on the posting and closing times of each job posting; and obtain the recruitment frequency of the target company's job postings based on the posting times of each job posting. S32. Obtain the recruitment frequency, duration of each recruitment, number of recruits, and daily online recruitment duration of each competitor's recruitment positions from the recruitment platform. Then, calculate the average of each of these values ​​and use them as the reference recruitment frequency, reference recruitment duration, reference number of recruits, and reference daily online recruitment duration, respectively, and denoted as f, T1, R, and T2. S33, Expression for the Recruitment Demand Assessment Model: In the formula, μ represents the assessment result of the recruitment demand for the target company's job posting, e represents the natural constant, f′ represents the recruitment frequency of the target company's job posting, and T1′ represents the recruitment frequency of the target company's job posting. c R c ′、T2′ c These represent the duration, number of openings, and daily online recruitment duration for the target company's job posting in the c-th recruitment session, respectively. c represents the recruitment session number, c is a positive integer, and C represents the total number of recruitment sessions. The preset threshold for assessing recruitment needs; μ = 1 indicates that the recruitment demand for the target company's job is high, while μ = -1 indicates that the recruitment demand for the target company's job is average.

5. The electronic recruitment matching method based on the Internet of Things according to claim 1, characterized in that, The process of selecting and upgrading job postings for target companies is as follows: We obtain the initial upgrade services corresponding to high demand from recruitment platforms. As each initial upgrade service, we obtain the recruitment quality assessment value, recruitment attraction value, recruitment effectiveness value, and recruitment attraction value of each upgrading company in each initial upgrade service and each competing company. Using the job posting data of the target company, the job posting data of each competitor, and the upgrade services, we calculate the recruitment attractiveness value of the target company and the recruitment attractiveness value of each competitor, and extract the recruitment quality assessment value of the target company's job postings. Then calculate the compatibility value between each initial upgrade service and the target enterprise, and select the initial upgrade service with the largest compatibility value as the target upgrade service.

6. The electronic recruitment matching method based on the Internet of Things according to claim 5, characterized in that, The specific calculation process for the recruitment attractiveness value of the target company is as follows: The click frequency of each potential job seeker for a specific job posting in the target company is obtained from the target company's job posting data and denoted as PZ. p We obtain the click frequency of each prospective job seeker for each job posting from the data of prospective job seekers for each competitor's job posting, denoted as PZ. jp Simultaneously, the scores of each prospective job seeker for the target company's job postings and the scores of each prospective job seeker for the job postings of each competing company are obtained and denoted as FZ respectively. p and FZ jp Let j represent the IDs of the competing companies, where j is a positive integer, and p represent the IDs of the prospective job seekers, where p is a positive integer. Using the calculation formula: The recruitment attractiveness value χ of the target company is obtained, where J represents the number of competing companies, P represents the number of prospective job seekers, and e represents the natural constant.

7. The electronic recruitment matching method based on the Internet of Things according to claim 6, characterized in that, The calculation process for the compatibility value between each initial upgrade service and the target enterprise is as follows: The recruitment attraction value of each upgraded company in each initial upgrade service is obtained by dividing the recruitment attraction value of each upgraded company by the average recruitment attraction value of each competing company. This value is denoted as χ². qy , where q represents the number of each initial upgrade service, y represents the number of each upgrade enterprise, and q and y are positive integers; Simultaneously, the recruitment quality assessment value and recruitment effectiveness value of each upgraded enterprise in each initial upgrade service are respectively denoted as ε. qy and σ qy And the recruitment quality assessment value of the target company's recruitment position is denoted as ε′, and then the calculation formula is used: The compatibility value φ between the q-th initial upgrade service and the target enterprise is obtained. q In the formula, Y and Q represent the number of upgraded enterprises and the number of initial upgrade services, respectively.

8. The electronic recruitment matching method based on the Internet of Things according to claim 1, characterized in that, The specific process for setting up the target company's recommendation data among the target job seekers is as follows: Using the job posting data of the target company and the resume data of the target job seeker, we obtain the score of the target job seeker in the target company. Similarly, we obtain the score of the target job seeker in each competing company. Then we analyze the initial competition level of the target company and each competing company in the target job seeker's opinion. The initial competition level is divided into three levels: Level 1, Level 2 and Level 3. If the target company's initial competition level among target job seekers is Level 1, obtain all competing companies with an initial competition level of Level 1 among target job seekers as each marked company. Obtain the average recommendation frequency of each marked company among job seekers from the recruitment platform's backend. Then, select the maximum average recommendation frequency as the reference recommendation frequency. Extract the recruitment attraction value of the target company and the recruitment attraction value of each marked company. If the recruitment attraction value of the target company is greater than the recruitment attraction value of each marked company, set the recommendation frequency of the target company among target job seekers to be 1.2 times the reference recommendation frequency. If the recruitment attraction value of the target company is less than the recruitment attraction value of at least one marked company, set the recommendation frequency of the target company among target job seekers to be 1.5 times the reference recommendation frequency. If the initial competitive level of the target company among the target job seekers is level two, the recommendation frequency of the target company among the target job seekers is set to 1.8 times the reference recommendation frequency; If the initial competition level of the target company among the target job seekers is level three, the recommendation frequency of the target company among the target job seekers is set to twice the reference recommendation frequency. This is used to obtain the recommendation frequency of the target company among the target job seekers as recommendation data.

9. The electronic recruitment matching method based on the Internet of Things according to claim 8, characterized in that, The initial competitive level analysis process for the target company among the target job seekers is as follows: The target score is the score of the target job seeker in the target company. The number of potential job seekers and suitable job seekers with the target score at the time of recruitment is obtained from the backend of the recruitment platform. The total number of marked job seekers is obtained. At the same time, the number of employees with the target score at the time of recruitment is obtained from the backend of the recruitment platform. The number of employees is divided by the number of marked job seekers to obtain the employment ratio of the target company. Similarly, the employment ratio of each competing company is obtained. Select the largest and smallest hiring ratios from the hiring ratios of the target company and each competitor company. Then add the largest and smallest hiring ratios together and divide by 2 to get the median hiring ratio. At the same time, select the mode from the hiring ratios of the target company and each competitor company as the mode hiring ratio. Then sort the largest, smallest, median, and mode hiring ratios in descending order and record them as the first hiring ratio, the second hiring ratio, the third hiring ratio, and the fourth hiring ratio, respectively. Among them, the range between the first and second recruitment ratios corresponds to the recruitment ratio range of level one in the initial competition level, the range between the second and third recruitment ratios corresponds to the recruitment ratio range of level two in the initial competition level, and the range between the third and fourth recruitment ratios corresponds to the recruitment ratio range of level three in the initial competition level. Then, based on the recruitment ratio of the target company, the initial competition level of the target company among the target job seekers is obtained.

10. An IoT-based electronic recruitment matching system that implements the IoT-based electronic recruitment matching method according to any one of claims 1-9, characterized in that, include: The recruitment data acquisition module is used to acquire recruitment description data, prospective job seeker data, and suitable job seeker data for the target company's job postings, as well as recruitment description data, prospective job seeker data, and suitable job seeker data for the job postings of competing companies. The recruitment data analysis module is used to analyze the recruitment quality of the target company's recruitment positions by utilizing the recruitment description data, prospective job seeker data, and suitable job seeker data of the target company's recruitment positions, as well as the recruitment description data and prospective job seeker data of the recruitment positions of various competing companies. The recruitment quality is divided into high quality and low quality. When the recruitment quality of the target company's recruitment positions is low, the recruitment upgrade analysis module is executed. The recruitment upgrade analysis module is used to obtain the job posting data of target companies, analyze the recruitment needs of target companies' job postings, including high demand and general demand, and obtain the upgrade services and posting data of job postings of various competing companies. It selects the target upgrade service for the job postings of the target company and displays and prompts the target company to upgrade. If the target company selects the upgrade, the recruitment matching module is executed when the target job seeker applies for the job. The recruitment matching module is used to obtain the resume data of target job seekers when they apply for jobs, analyze the matching situation between target job seekers and target companies, and if the matching situation is a match, set the target company's recommendation data on the target job seeker's side based on the target company's upgraded services. If the matching situation is a mismatch, no settings are made.

Images