Enterprise service post function analysis and management method based on big data

Abstract

The invention discloses an enterprise service post function analysis and management method based on big data, and relates to the technical field of data mining, and the method comprises the steps: obtaining the big data of applicants based on a database API interface of a talent recruitment platform, and constructing an applicant database; based on the function range of the enterprise vacant posts, task types covered by the function range are analyzed, and the function requirements of the enterprise vacant posts are quantified; performing association matching with an applicant database according to the function requirements of the enterprise vacant posts, screening out applicants meeting the function requirements, substituting the applicants into role positioning of a team where the enterprise vacant posts are located, and analyzing the degree of adaptation between each candidate person and the team where the enterprise vacant posts are located; and marking the candidate person with the optimal adaptation degree, and generating an enterprise vacant post recruitment task. The method has the advantages that the degree of fitting between the enterprise recruiters and the posts is improved, and meanwhile the cooperation level between the whole teams is maximized.

Description

Technical Field

[0001] The present invention relates to the technical field of data mining, and in particular to an enterprise service position function analysis and management method based on big data. Background Art

[0002] The enterprise service job function analysis and management of big data aims to provide enterprises with professional and efficient big data recruitment services by deeply analyzing the functional requirements of big data related positions, accurately matching and introducing top big data talents to promote the business development of enterprises.

[0003] The existing targeted corporate recruitment services focus on the skills and technical capabilities of applicants, but ignore the positioning of applicants in the team where the company's vacant positions are located. This results in a poor fit between the incoming applicants and the overall team, leading to low overall team assistance efficiency. Summary of the invention

[0004] In order to solve the above technical problems, a big data-based enterprise service job function analysis and management method is provided. This technical solution solves the problem that the existing targeted enterprise recruitment services focus on the skills and technical capabilities of applicants, but ignore the positioning of applicants in the team where the company's vacant positions are located, resulting in a poor fit between the incoming applicants and the overall team, leading to low assistance efficiency for the overall team.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] The enterprise service job function analysis and management method based on big data includes:

[0007] Based on the database API interface of the talent recruitment platform, we can obtain big data of candidates and build a candidate database;

[0008] Based on the functional scope of the company's vacant positions, analyze the types of tasks covered by the functional scope and quantify the functional requirements of the company's vacant positions;

[0009] According to the functional requirements of the company's vacant positions and the candidate database, we will match them, select candidates who meet the functional requirements, substitute them into the role positioning of the team where the vacant positions are located, and analyze the compatibility between each candidate and the team where the vacant positions are located;

[0010] Mark the candidates with the best suitability and generate recruitment tasks for company vacant positions.

[0011] Preferably, based on the functional scope of the company's vacant positions, analyze the types of tasks covered by the functional scope and quantify the functional requirements of the company's vacant positions, including:

[0012] Based on the functional scope of the vacant position, split the task types covered by the functional scope into several subtasks;

[0013] Divide the task types covered by the functional scope into several subtasks, mark the corresponding skill requirements of each subtask, and construct the skill requirement matrix A for vacant positions;

[0014]

[0015] Among them, x ij is the jth skill requirement of the i-th vacant position, m is the total number of vacancies, and n is the total number of skill requirements;

[0016] Based on the skill requirement matrix for vacant positions, set the skill requirement weights for vacant positions according to the importance of the subtasks of the task types covered by the functional scope to the overall project;

[0017] Calculate the functional requirements of the company's vacant positions based on each element in the job skill requirement matrix and the skill requirement weight of the vacant positions;

[0018] Among them, the functional requirements of the company's vacant positions are specifically as follows:

[0019]

[0020] In the formula, x′ ij is the quantitative value of the jth skill requirement for the i-th vacant position, w j is the j-th skill requirement weight.

[0021] Preferably, the functional requirements of the company's vacant positions are matched with the candidate database, and candidates who meet the functional requirements are screened out. The candidates are substituted into the role positioning of the team where the company's vacant positions are located, and the compatibility between each candidate and the team where the company's vacant positions are located is analyzed. Specifically, it includes:

[0022] Based on the skill requirements of vacant positions, a technical category vocabulary of skill requirements of vacant positions is established with texts of several technical categories that meet the skill requirements;

[0023] Create a TF-DIF assignment function, calculate the TF-DIF value of the text of the technical category that meets the skill requirements of each vacant position based on the skill requirement technical category vocabulary, and select the technical category with a TF-DIF higher than the mean as the technical category feature, and establish the technical category feature vector matrix B of the skill requirements;

[0024]

[0025] Among them, y ikis the feature vector of the kth technology category that meets the i-th skill requirement, and l is the total number of feature vectors of technology categories that meet the skill requirement;

[0026] Based on the candidate database, standardize the candidate data to obtain standardized talent resume data;

[0027] Based on the standardized resume data, the word segmentation function is used to remove the high and low frequency words in the resume data of the applicants to obtain the text feature data set of the applicants;

[0028] Based on the candidate text feature dataset, substitute it into the TF-DIF assignment function to generate the technical capability feature vector of each candidate;

[0029] Based on the correlation matching between the technical capability feature vector of each applicant and the technical category feature vector matrix of the skill requirements, applicants of technical categories that meet the skill requirements of the vacant positions are screened out and recorded as the initial screening candidates;

[0030] Substitute the initially screened candidates into the role positioning of the team where the company's vacant positions are located, and analyze the compatibility between each candidate and the team where the company's vacant positions are located;

[0031] The specific method of associating and matching the technical capability feature vector of each applicant with the technical category feature vector matrix of skill requirements is as follows:

[0032]

[0033] In the formula, Simil(y ik ,S k ) is the cosine similarity matching function, S vk is the technical capability feature vector of the kth technical category of the vth applicant.

[0034] Preferably, the initially screened candidates are placed in the role positioning of the team where the vacant position is located in the enterprise, and the compatibility between each candidate and the team where the vacant position is located in the enterprise is analyzed, including:

[0035] Obtain multi-dimensional data of each team member and calculate multi-dimensional comprehensive indicators of the entire team; the multi-dimensional data includes: educational background, work experience, interests and hobbies;

[0036] Use linear transformation to map the multi-dimensional comprehensive indicators of the entire team into the multi-dimensional space vector of the entire team;

[0037] For the resume data of the initial screening candidates, PCA dimensionality reduction processing is used to calculate the spatial distance between the multi-dimensional resume data of the initial screening candidates and the team behavior preference space vector for normalization processing to obtain the degree of fit between the candidate and the team where the vacant position of the enterprise is located;

[0038] The multi-dimensional comprehensive indicators for calculating the overall team are as follows:

[0039]

[0040] Where P j′ For the overall team ′ Comprehensive indicators of dimensions, D i′j′ For the i ′ The jth member ′ Dimensional data, β j′ For the jth ′ The weight of the dimension, n ′ is the total number of multi-dimensional composite indicators;

[0041] The degree of compatibility between the candidate and the team of the company's vacant position is specifically:

[0042]

[0043] In the formula, G is the degree of fit between the candidate and the team of the company's vacant position, P ′ j′ For the overall team ′ dimensional space vector, U zj′ is the jth candidate of the zth candidate ′ Dimensional data.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention proposes an enterprise service job function analysis and management plan based on big data, performs correlation matching on the data of job applicants based on the job function requirements of the enterprise, screens out candidates who meet the requirements, substitutes the candidates into the role positioning of the team where the vacant positions of the enterprise are located, analyzes the fit between the candidates and the overall team, determines the best candidates, and determines the recruitment targets; the beneficial effects are: while improving the fit between the enterprise recruiters and the positions, the level of collaboration between the overall team is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 Provide a flow chart of the management method for analyzing the job functions of enterprise services based on big data;

[0047] Figure 2 A flow chart of the method to quantify the functional requirements of vacant positions in an enterprise;

[0048] Figure 3 A flow chart of the method to screen out candidates who meet the job requirements;

[0049] Figure 4 A flow chart of the method for determining the fit between candidates and the team of the company's vacant positions. DETAILED DESCRIPTION

[0050] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0051] Reference Figure 1 As shown in the figure, the enterprise service position function analysis and management method based on big data includes:

[0052] Based on the database API interface of the talent recruitment platform, we can obtain big data of candidates and build a database of candidates;

[0053] Based on the functional scope of the company's vacant positions, analyze the types of tasks covered by the functional scope and quantify the functional requirements of the company's vacant positions;

[0054] According to the functional requirements of the company's vacant positions and the candidate database, we will match them, select candidates who meet the functional requirements, substitute them into the role positioning of the team where the vacant positions are located, and analyze the compatibility between each candidate and the team where the vacant positions are located;

[0055] Mark the candidates with the best suitability and generate recruitment tasks for company vacant positions.

[0056] This solution matches the data of job applicants based on the job function requirements of the enterprise, selects candidates who meet the requirements, substitutes the candidates into the role positioning of the team where the vacant positions are located, analyzes the fit between the candidates and the overall team, determines the best candidates, and determines the recruitment targets; the beneficial effect is: while improving the fit between the enterprise recruiters and the positions, it maximizes the level of collaboration between the overall team;

[0057] Reference Figure 2 As shown in the figure, based on the functional scope of the company's vacant positions, the types of tasks covered by the functional scope are analyzed, and the functional requirements of the company's vacant positions are quantified, including:

[0058] Based on the functional scope of the vacant position, split the task types covered by the functional scope into several subtasks;

[0059] Divide the task types covered by the functional scope into several subtasks, mark the corresponding skill requirements of each subtask, and construct the skill requirement matrix A for vacant positions;

[0060]

[0061] Among them, x ij is the jth skill requirement of the i-th vacant position, m is the total number of vacancies, and n is the total number of skill requirements;

[0062] Based on the skill requirement matrix for vacant positions, set the skill requirement weights for vacant positions according to the importance of the subtasks of the task types covered by the functional scope to the overall project;

[0063] Calculate the functional requirements of the company's vacant positions based on each element in the job skill requirement matrix and the skill requirement weight of the vacant positions;

[0064] Among them, the functional requirements of the company's vacant positions are specifically as follows:

[0065]

[0066] In the formula, x′ ij is the quantitative value of the jth skill requirement for the i-th vacant position, w j is the j-th skill requirement weight.

[0067] It should be noted that the skill requirement for vacant positions is a binary variable, where 1 is when the requirement is met and 0 is when the requirement is not met.

[0068] It can be understood that the task types covered by the functional scope of an enterprise's vacant positions refer to the required skills and knowledge proficiency. For example, a food delivery project includes front-end engineers, back-end engineers, artists and architects from project establishment to launch. The task types covered by the corresponding vacancies have the highest importance weight for the overall project. The front-end and back-end are the same, and the artist has the lowest importance weight. Therefore, after the task types of the overall project are divided into multiple sub-tasks, they are weighted according to the corresponding skill requirements of the sub-tasks, and the functional requirements of the enterprise's vacant positions are calculated to reduce inaccurate recommendations caused by conventional OCR recognition.

[0069] Reference Figure 3 As shown, the functional requirements of the company's vacant positions are associated with the candidate database, and candidates who meet the functional requirements are screened out. The role positioning of the team where the company's vacant positions are located is substituted, and the compatibility between each candidate and the team where the company's vacant positions are located is analyzed. The specific details include:

[0070] Based on the skill requirements of vacant positions, a technical category vocabulary of skill requirements of vacant positions is established with texts of several technical categories that meet the skill requirements;

[0071] Create a TF-DIF assignment function, calculate the TF-DIF value of the text of the technical category that meets the skill requirements of each vacant position based on the skill requirement technical category vocabulary, and select the technical category with a TF-DIF higher than the mean as the technical category feature, and establish the technical category feature vector matrix B of the skill requirements;

[0072]

[0073] Among them, y ik is the feature vector of the kth technology category that meets the i-th skill requirement, and l is the total number of feature vectors of technology categories that meet the skill requirement;

[0074] Based on the candidate database, standardize the candidate data to obtain standardized talent resume data;

[0075] Based on the standardized resume data, the word segmentation function is used to remove the high and low frequency words in the resume data of the applicants to obtain the text feature data set of the applicants;

[0076] Based on the candidate text feature dataset, substitute it into the TF-DIF assignment function to generate the technical capability feature vector of each candidate;

[0077] Based on the correlation matching between the technical capability feature vector of each applicant and the technical category feature vector matrix of the skill requirements, applicants of technical categories that meet the skill requirements of the vacant positions are screened out and recorded as the initial screening candidates;

[0078] Substitute the initially screened candidates into the role positioning of the team where the company's vacant positions are located, and analyze the compatibility between each candidate and the team where the company's vacant positions are located;

[0079] The specific method of associating and matching the technical capability feature vector of each applicant with the technical category feature vector matrix of skill requirements is as follows:

[0080]

[0081] In the formula, Simil(y ik ,S k ) is the cosine similarity matching function, S vk is the technical capability feature vector of the kth technical category of the vth applicant.

[0082] This solution quantifies the technical type vector of the company's job skill requirements and the technical ability feature vector of the applicants, accurately matching the skill requirements of vacant positions with the technical capabilities of applicants, thereby improving the accuracy and efficiency of recruitment. Secondly, the TF-IDF method is used to screen out key technical category features, which helps to quickly locate qualified candidates and improve the company's overall recruitment quality.

[0083] Reference Figure 4 As shown in the figure, the initial screening candidates are substituted into the role positioning of the team where the vacant position is located in the enterprise, and the compatibility between each candidate and the team where the vacant position is located in the enterprise is analyzed. Specifically, the following are included:

[0084] Obtain multi-dimensional data of each team member and calculate multi-dimensional comprehensive indicators of the entire team; the multi-dimensional data includes: educational background, work experience, interests and hobbies;

[0085] Use linear transformation to map the multi-dimensional comprehensive indicators of the entire team into the multi-dimensional space vector of the entire team;

[0086] For the resume data of the initial screening candidates, PCA dimensionality reduction processing is used to calculate the spatial distance between the multi-dimensional resume data of the initial screening candidates and the team behavior preference space vector for normalization processing to obtain the degree of fit between the candidate and the team where the vacant position of the enterprise is located;

[0087] The multi-dimensional comprehensive indicators for calculating the overall team are as follows:

[0088]

[0089] Where P j′ For the overall team ′ Comprehensive indicators of dimensions, D i′j′ For the i ′ The jth member ′ Dimensional data, β j′ For the jth ′ The weight of the dimension, n ′ is the total number of multi-dimensional composite indicators;

[0090] The degree of compatibility between the candidate and the team of the company's vacant position is specifically:

[0091]

[0092] In the formula, G is the degree of fit between the candidate and the team of the company's vacant position, P ′ j′ For the overall team ′ dimensional space vector, U zj′ is the jth candidate of the zth candidate′ Dimensional data.

[0093] It is understandable that by objectively evaluating the degree of fit between candidates and the team, the one-sidedness of single-dimensional evaluation is avoided. Through quantitative analysis, the accuracy and efficiency of recruitment decisions are improved, which helps companies select the most suitable team members for vacant positions, thereby improving the overall performance and collaboration efficiency of the team.

[0094] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An enterprise service position function analysis and management method based on big data, characterized in that: include: Based on the database API interface of the talent recruitment platform, we can obtain big data of candidates and build a database of candidates; Based on the functional scope of the company's vacant positions, analyze the types of tasks covered by the functional scope and quantify the functional requirements of the company's vacant positions; According to the functional requirements of the company's vacant positions and the candidate database, we will match them, select candidates who meet the functional requirements, substitute them into the role positioning of the team where the vacant positions are located, and analyze the compatibility between each candidate and the team where the vacant positions are located; Mark the candidates with the best suitability and generate recruitment tasks for company vacant positions.

2. The enterprise service position function analysis and management method based on big data according to claim 1 is characterized in that: Based on the functional scope of the company's vacant positions, analyze the types of tasks covered by the functional scope and quantify the functional requirements of the company's vacant positions, including: Based on the functional scope of the vacant position, split the task types covered by the functional scope into several subtasks; Divide the task types covered by the functional scope into several subtasks, mark the corresponding skill requirements of each subtask, and construct the skill requirement matrix A for vacant positions; Among them, x ij is the jth skill requirement of the i-th vacant position, m is the total number of vacancies, and n is the total number of skill requirements; Based on the skill requirement matrix for vacant positions, set the skill requirement weights for vacant positions according to the importance of the subtasks of the task types covered by the functional scope to the overall project; Based on each element in the job skill requirement matrix and the skill requirement weight of the vacant job, the functional requirements of the company's vacant jobs are calculated.

3. The enterprise service position function analysis and management method based on big data according to claim 2 is characterized in that: The specific functional requirements of the company's vacant positions are: In the formula, x′ ij is the quantitative value of the jth skill requirement for the i-th vacant position, w j is the j-th skill requirement weight.

4. The enterprise service position function analysis and management method based on big data according to claim 3 is characterized in that: According to the functional requirements of the company's vacant positions and the candidate database, we will screen out candidates who meet the functional requirements, substitute them into the role positioning of the team where the vacant positions are located, and analyze the compatibility between each candidate and the team where the vacant positions are located. The specific details include: Based on the skill requirements of vacant positions, a technical category vocabulary of skill requirements of vacant positions is established with texts of several technical categories that meet the skill requirements; Create a TF-DIF assignment function, calculate the TF-DIF value of the text of the technical category that meets the skill requirements of each vacant position based on the skill requirement technical category vocabulary, and select the technical category with a TF-DIF higher than the mean as the technical category feature, and establish the technical category feature vector matrix B of the skill requirements; Among them, y ik is the feature vector of the kth technology category that meets the i-th skill requirement, and l is the total number of feature vectors of technology categories that meet the skill requirement; Based on the candidate database, standardize the candidate data to obtain standardized talent resume data; Based on the standardized resume data, the word segmentation function is used to remove the high and low frequency words in the resume data of the applicants to obtain the text feature data set of the applicants; Based on the candidate text feature dataset, substitute it into the TF-DIF assignment function to generate the technical capability feature vector of each candidate; Based on the correlation matching between the technical capability feature vector of each applicant and the technical category feature vector matrix of the skill requirements, applicants of technical categories that meet the skill requirements of the vacant positions are screened out and recorded as the initial screening candidates; Substitute the initially screened candidates into the role positioning of the team where the company's vacant positions are located, and analyze the compatibility between each candidate and the team where the company's vacant positions are located.

5. The enterprise service position function analysis and management method based on big data according to claim 4 is characterized in that: The specific method of associating and matching the technical capability feature vector of each candidate with the technical category feature vector matrix of the skill requirements is as follows: In the formula, Simil(y ik ,S k ) is the cosine similarity matching function, S vk is the technical capability feature vector of the kth technical category of the vth applicant.

6. The enterprise service position function analysis and management method based on big data according to claim 5 is characterized in that: Substitute the initially screened candidates into the role positioning of the team where the company's vacant positions are located, and analyze the compatibility between each candidate and the team where the company's vacant positions are located, including: Obtain multi-dimensional data of each team member and calculate multi-dimensional comprehensive indicators of the entire team; the multi-dimensional data includes: educational background, work experience, interests and hobbies; Use linear transformation to map the multi-dimensional comprehensive indicators of the entire team into the multi-dimensional space vector of the entire team; For the resume data of the initial screening candidates, PCA dimensionality reduction processing is used to calculate the spatial distance between the multi-dimensional data of the resume of the initial screening candidates and the team behavior preference space vector, and then normalize it to obtain the degree of fit between the candidate and the team where the vacant position is located in the enterprise.

7. The enterprise service position function analysis and management method based on big data according to claim 6 is characterized in that: The multi-dimensional comprehensive indicators for calculating the overall team are specifically: Where P j′ For the overall team ′ Comprehensive indicators of dimensions, D i′j′ For the i ′ The jth member ′ Dimensional data, β j′ For the jth ′ The weight of the dimension, n ′ is the total number of multi-dimensional composite indicators; The degree of compatibility between the candidate and the team of the company's vacant position is specifically: In the formula, G is the degree of fit between the candidate and the team of the company's vacant position, P ′ j′ For the overall team ′ dimensional space vector, U zj′ is the jth candidate of the zth candidate ′ Dimensional data.

Images