Enterprise personnel management optimization method and system based on big data statistical analysis

Abstract

The invention discloses an enterprise personnel management optimization method and system based on big data statistical analysis. The method comprises the steps of collecting personnel data such as enterprise employee basic information, post job information and salary issuing information, and performing classified storage; calling a human cost elasticity prediction model to obtain a post level cost elasticity coefficient, starting a skill growth path planning model to generate an employee personalized skill growth scheme, and operating an employee portrait three-dimensional evaluation model to construct an employee three-dimensional portrait; a result is imported into a talent pool dynamic operation management platform, and talent pool grades and allocation priorities are divided after integration and analysis; and a personnel management optimization execution scheme is formulated by combining parameters such as post vacancy and salary adjustment. According to the system, through multi-model cooperation and data linkage, efficient personnel data processing, accurate human cost prediction, scientific staff development planning and reasonable talent resource allocation are realized, and the enterprise personnel management refinement and dynamic adaptation capability is improved.

Description

Technical Field

[0001] This invention relates to the field of enterprise human resource management technology, and in particular to an enterprise human resource management optimization method and system based on big data statistical analysis. Background Technology

[0002] As businesses continue to expand, the amount of employee data involved in human resources management grows exponentially, including basic employee information, job descriptions, payroll, performance appraisals, and training participation. Traditional HR management models, relying on manual statistics and experience-based judgment, are struggling to efficiently process massive amounts of data, accurately grasp the patterns of changing labor costs, develop personalized employee development paths, and scientifically categorize talent pools. Against the backdrop of intensifying market competition, businesses increasingly demand more refined, dynamic, and efficient HR management. They urgently need to leverage big data statistical analysis technology to integrate functions such as flexible labor cost forecasting, skills development path planning, employee profiling, and talent pool operation and management to build a systematic HR management optimization solution that can adapt to the dynamic needs of businesses in areas such as filling vacancyes, adjusting salaries, and allocating training resources during their development.

[0003] Existing technologies in the field of enterprise human resource management have two significant drawbacks: First, human resource cost forecasting lacks systematic model support and relies heavily on simple extrapolation from historical data. It fails to fully integrate key parameters such as salary changes at different job levels, enterprise size, and historical cost fluctuations, resulting in low elasticity between forecast results and actual human resource costs, making it difficult to provide accurate basis for enterprise salary adjustments. Second, employee development planning is disconnected from talent pool management. Skills development path formulation is not effectively linked to employee training effectiveness and job skill requirements matching. Employee profile construction does not fully cover the three dimensions of ability, attitude, and potential. Furthermore, the classification of talent pool levels and the determination of allocation priorities do not integrate human resource cost, employee skills development, and profile assessment data, making it impossible to achieve efficient allocation of human resources and meet the comprehensive needs of enterprise human resource management optimization. Summary of the Invention

[0004] In order to overcome the shortcomings and deficiencies of existing technologies, this invention provides a method and system for optimizing enterprise human resource management based on big data statistical analysis.

[0005] The technical solution adopted in this invention is a method for optimizing enterprise human resource management based on big data statistical analysis, comprising the following steps: S1, collecting internal human resource data, including employee basic information, job information, salary payment information, performance appraisal information, and training participation information, and transmitting the collected human resource data to a data storage module for classified storage; S2, calling a human resource cost elasticity prediction model, inputting the stored salary payment information, job information, and historical human resource cost adjustment data of the enterprise, and obtaining human resource cost elasticity coefficients for different job levels through model calculation; S3, activating a skills development path planning model, importing employee training participation information, performance appraisal information, and job skill requirement standard data, and generating a personalized skills development path plan for each employee through model processing. S4. Run the three-dimensional employee profile assessment model, using basic employee information, performance appraisal information, and training participation information as input data, to calculate the employee's assessment scores in the ability, attitude, and potential dimensions, thus constructing a three-dimensional employee profile. S5. Import the human resource cost elasticity coefficient obtained in S2, the personalized skill development path plan generated in S3, and the three-dimensional employee profile constructed in S4 into the talent pool dynamic operation management platform. The platform integrates and analyzes the data, classifies the talent pool into levels, and determines the allocation priority for different levels of talent. S6. Based on the analysis results of the talent pool dynamic operation management platform, combined with the enterprise's HR management optimization parameters for job vacancy, salary adjustment, and training resource allocation, formulate an enterprise HR management optimization implementation plan and feed it back to the enterprise's HR management department.

[0006] Furthermore, the expression for the labor cost elasticity prediction model is as follows: ,in, This represents the elasticity coefficient of labor costs. For the number of job types, For the first Weighting coefficients for job categories For the first The difference in labor costs between the current and previous periods for this type of job. For the first Previous period labor costs for similar positions For the first Average salary of this type of position in the previous period For the first The difference between the average salary of this type of job in the current period and the previous period. The influence coefficient of enterprise size. The historical human resource cost fluctuation index of the enterprise is used; the parameters for optimizing the enterprise's human resource management include the number of job types, job weight coefficient, enterprise size influence coefficient, and historical human resource cost fluctuation index.

[0007] Furthermore, the expression for the skill development path planning model is: ,in, A comprehensive score for the skills development path. For the number of skill modules, For the first The importance coefficient of each skill module For the current employee The score for mastery of each skill module, For the first The training effectiveness coefficient corresponding to each skill module For employee participation The duration of training for each skill module, The parameters for optimizing enterprise human resource management include the number of skill modules, the importance coefficient of skill modules, the training effectiveness coefficient of skill modules, and the matching degree of job skill requirements.

[0008] Furthermore, the expression for the three-dimensional employee profile evaluation model is as follows: ,in, Three-dimensional evaluation vector for employee profiling. , These are the weighting coefficients for the ability dimension, attitude dimension, and potential dimension, respectively. Scoring based on ability dimensions Rate the attitude dimension. Score based on potential dimension. These are the evaluation error correction values ​​for the three dimensions; the parameters for optimizing enterprise human resource management include the three-dimensional weight coefficients and the three-dimensional evaluation error correction values.

[0009] Furthermore, the data integration and analysis of the talent pool dynamic operation management platform adopts the following model: ,in, To allocate priority scores to the talent pool As the weight of the elasticity coefficient of labor costs, As a weighted factor in the overall score of skills development path, Employee profiling: a three-dimensional evaluation vector weighting. This represents the current capacity coefficient of the talent pool. The urgency coefficient for job vacancies; the parameters for optimizing enterprise human resource management include different data weights, talent pool capacity coefficient, and job vacancy urgency coefficient.

[0010] Furthermore, the model used in formulating the enterprise human resource management optimization implementation plan is as follows: ,in, To optimize the execution priority of the plan, To allocate priority scores and weights to the talent pool This is the salary adjustment range coefficient. Adjust the budget amount for salaries. For the allocation coefficient of training resources, The total amount of training resources; the parameters for optimizing enterprise human resource management include execution priority weight, salary adjustment range coefficient, salary adjustment budget amount, training resource allocation coefficient, and total amount of training resources.

[0011] Further, S3 includes the following sub-steps: S31, extracting employee training participation information from the data storage module for the past three assessment cycles, filtering out the types of training projects the employee has participated in, training duration, and training assessment results, and establishing an employee training information dataset; S32, collecting skill requirement standard data for different positions within the company, including the types of skills required for the position, the mastery requirements for different skills, and the skill update cycle, forming a job skill requirement standard library; S33, matching the employee training information dataset with the job skill requirement standard library, identifying the gap between the skills currently mastered by the employee and the skills required for the position, and determining the skill modules that need to be supplemented; S34, based on the skill modules that need to be supplemented, combined with the company's existing training resources and skill update cycle, assigning corresponding training projects to employees, and generating personalized skill growth path plans arranged in chronological order.

[0012] Further, S4 includes the following sub-steps: S41, based on the employee's basic information, extract data on the employee's education, professional background, years of service, and tenure in the position as the basic input data for the competency dimension assessment; S42, organize the employee's performance appraisal information for the past two years, and select data on work completion rate, on-time delivery rate, and teamwork scoring indicators as the core input data for the attitude dimension assessment; S43, analyze the employee's active registration rate for training, the foresight of training course selection, and the trend of improvement in assessment results to obtain data related to the employee's learning willingness and development potential as the calibration input data for the potential dimension assessment; S44, substitute the input data of the three dimensions into the three-dimensional employee profile assessment model, calculate the assessment scores for different dimensions, and construct a three-dimensional employee profile including competency, attitude, and potential dimension scores through vector integration.

[0013] Further, S5 includes the following sub-steps: S51, receiving the human cost elasticity coefficients for different job levels output by S2, normalizing the coefficients, establishing a human cost elasticity coefficient database and associating it with corresponding job information; S52, importing the personalized skill development path plan for each employee generated in step S3, extracting the skill improvement goals and training cycle calibration information from the plan, and constructing an employee skill development information database; S53, retrieving the employee three-dimensional profile formed in step S4, sorting it in descending order according to the ability dimension score, dividing it into three ability level ranges of high, medium, and low, and establishing an employee ability level classification database; S54, importing the data from the human cost elasticity coefficient database, the employee skill development information database, and the employee ability level classification database into the talent pool dynamic operation management platform, the platform integrating multi-database data through a data association algorithm, classifying the talent pool levels based on the integration results, and calculating the allocation priority of different levels of talent.

[0014] This enterprise HR management optimization system, based on big data statistical analysis, utilizes a method for optimizing HR management using big data statistical analysis. It includes: a multi-source HR data collection and classification storage unit, which collects basic employee information, job information, salary payment information, performance appraisal information, and training participation information, classifies and stores the collected information, and establishes a data transmission connection with the subsequent data processing unit, sending the classified HR data to the data processing unit; a human resource cost elasticity prediction and calculation unit, which receives salary payment information, job information, and historical human resource cost adjustment data transmitted from the multi-source HR data collection and classification storage unit, calls a preset human resource cost elasticity prediction model to perform calculations, generates human resource cost elasticity coefficients for different job levels, and transmits the coefficients to the talent pool dynamic operation unit; and an employee skill development path planning and generation unit, which obtains employee training participation information, performance appraisal information, and job skill requirement standard data from the multi-source HR data collection and classification storage unit, processes it through a skill development path planning model to generate personalized skill development path plans, and sends the plans to the talent pool dynamic operation unit; and so on. The employee three-dimensional profile construction and evaluation unit receives basic employee information, performance appraisal information, and training participation information from the multi-source data collection and classification storage unit. It then runs the employee profile three-dimensional evaluation model to calculate evaluation scores for different dimensions, constructs a three-dimensional employee profile, and transmits it to the talent pool dynamic operation unit. The talent pool dynamic operation and data analysis unit establishes data receiving connections with the human resource cost elasticity prediction and calculation unit, the employee skill development path planning and generation unit, and the employee three-dimensional profile construction and evaluation unit. It integrates and analyzes the received human resource cost elasticity coefficient, skill development path plan, and employee three-dimensional profile, classifies the talent pool into levels, determines allocation priorities, and interacts with the human resource management optimization plan formulation unit. The human resource management optimization plan formulation and feedback unit receives the analysis results output by the talent pool dynamic operation and data analysis unit. Combining these with the enterprise's human resource management optimization parameters such as job vacancy parameters, salary adjustment parameters, and training resource allocation parameters, it formulates an optimization implementation plan and feeds it back to the enterprise's human resource management department. This unit maintains real-time data communication with the talent pool dynamic operation and data analysis unit to ensure the timeliness of the plan formulation.

[0015] Beneficial Effects: This invention proposes a method and system for optimizing enterprise human resource management based on big data statistical analysis. It can efficiently process massive amounts of enterprise human resource data, accurately outputting human resource cost elasticity coefficients, personalized skill development path plans, and three-dimensional employee profiles. This provides a scientific basis for talent pool classification and priority allocation, helping enterprises formulate human resource management optimization plans that meet the needs of job vacancies, salary adjustments, and training resource allocation, improving the refinement and dynamism of human resource management, and achieving efficient allocation of talent resources. Simultaneously, addressing the lack of a systematic model for human resource cost prediction, the system utilizes a human resource cost elasticity prediction model, fully integrating key parameters such as job level salary changes, enterprise size, and historical cost fluctuations to improve the alignment between prediction results and actual human resource cost elasticity, providing a precise basis for salary adjustments. Addressing the disconnect between employee development planning and talent pool management, the system links training effectiveness with job skill requirements through a skill development path planning model. It relies on a three-dimensional employee profile assessment model to comprehensively cover ability, attitude, and potential dimensions, and then integrates multi-dimensional data through a dynamic talent pool operation and management platform, achieving linkage between employee development planning and talent pool management, and meeting the comprehensive needs of enterprise human resource management optimization. Attached Figure Description

[0016] Figure 1 This is a flowchart of the method steps of the present invention; Figure 2 This is a diagram showing the system unit composition of the present invention. Detailed Implementation

[0017] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0018] like Figure 1 As shown, the enterprise human resource management optimization method based on big data statistical analysis includes the following steps: S1. Collect internal personnel data of the enterprise. The personnel data includes basic employee information, job information, salary payment information, performance appraisal information and training participation information. The collected personnel data is transmitted to the data storage module for classified storage. Specifically, step S1 involves the collection and classification of enterprise personnel data. During implementation, data needs to be collected through multiple data sources (including the enterprise HR system, attendance system, payroll system, training management system, and performance appraisal system). The collection cycle is set to collect employee basic information change data in real time, daily attendance and training participation data, and monthly payroll and performance appraisal data to ensure data timeliness. The collected personnel data must include employee basic information (including 12 core fields such as name, gender, age, education, date of employment, and job number), job information (including 8 fields such as job title, job level, job description, and qualification requirements), payroll information (including 10 fields such as monthly basic salary, performance bonus, subsidies, and social security contributions), and performance appraisal information (including assessment results). The data collection process includes six fields: cycle, assessment dimension score, comprehensive rating, and improvement suggestions, as well as seven fields: training participation information (training project name, training duration, training assessment results, and training completion time). After collection, the data is cleaned (null and outlier values ​​are removed; outlier values ​​are defined as data deviating from the average of the field by more than three standard deviations). The data is then categorized by data type and stored in a distributed database (using HDFS storage architecture, with a single data block size set to 128MB and three replicas to ensure data security). An index label is created for each data type (e.g., "Employee Basic Information - Job Number - 2025") to facilitate rapid retrieval during subsequent model calls. This step provides complete and accurate data source support for subsequent model calculations, avoiding deviations in subsequent analysis results due to missing or incorrect data.

[0019] S2, call the human resource cost elasticity prediction model, input the stored salary payment information, job information and the company's historical human resource cost adjustment data, and obtain the human resource cost elasticity coefficient for different job levels through model calculation; Specifically, step S2 involves calling the human resource cost elasticity prediction model and calculating the elasticity coefficient. During implementation, input data is first extracted from the categorized database. This includes extracting the average monthly salary and salary adjustment range for each job level over the past three years for salary payment information; extracting the number of employees and employee turnover rate (calculated as annual departures / average annual on-the-job staff) for job position information; and extracting the total human resource cost and the ratio of human resource cost to revenue for the past five years for historical human resource cost adjustment data. After extraction, the data is standardized (converting data of different magnitudes to the [0,1] range), and then input into the human resource cost elasticity prediction model. During model calculation, different weights are assigned to each parameter (job level weights are based on the base...). The weighting is distributed as follows: 30% for senior management, 40% for middle management, and 30% for senior management; 25% for salary adjustment magnitude; 20% for employee turnover rate; and 25% for historical cost adjustment data. Simultaneously, it is adjusted using industry benchmark values ​​for human cost elasticity (obtained from an industry database, such as 1.2 for entry-level positions and 1.5 for middle management in manufacturing). The calculation cycle is controlled within one hour, ultimately outputting the human cost elasticity coefficient for each job level (with a value range of 0.8-2.0; a coefficient greater than 1 indicates that human costs are sensitive to salary adjustments). This step accurately reflects the changing patterns of human costs at different job levels, providing a quantitative basis for setting subsequent salary adjustment parameters and solving the problem of traditional human cost forecasting relying on experience.

[0020] S3 enables the skills development path planning model, imports employee training participation information, performance appraisal information, and job skill requirement standard data, and generates a personalized skills development path plan for each employee after model processing. Specifically, step S3 involves activating the skills development path planning model and generating personalized solutions. During implementation, the employee's training participation information for the past two assessment cycles is extracted from the data storage module (including assessment scores for participated training projects and required training projects not participated in), and skill dimension scores from the past three performance appraisals (e.g., professional skills, operational skills, collaborative skills, etc., each with a maximum score of 100 points). Simultaneously, skill requirement data for the corresponding position is retrieved from the company's job skill standard library (including core skill types; typically, each position has 3-5 core skills, mastery requirements for each skill, divided into three levels: basic, proficient, and expert, with corresponding score ranges below 60 points, 60-89 points, and 90-100 points respectively, and skill update cycles: 6-12 months for technical positions and 12-24 months for management positions). The employee's existing skill data is then compared with the job requirement data to calculate the skill gap (e.g., a certain employee's skill gap). If the core skills score is 75 points and the job requirement is 80 points (proficient level), the gap is 5 points. The skill improvement priority is determined by combining the employee's skill improvement speed (difference between the skill scores of the two most recent assessments / number of months between assessments). Then, the skill gap, priority, and existing company training resource data (including available training programs, training schedules, and number of instructors) are input into the skills development path planning model. The model is divided into short-term (1-3 months), medium-term (4-6 months), and long-term (7-12 months) phases, with 1-2 training programs allocated to each phase (to avoid training overload). The skill improvement goals for each phase are clearly defined (e.g., improving a skill from 75 to 80 points in the short term) and assessment requirements. A structured, personalized skills development path plan is generated and simultaneously stored in the employee's personal file and training management system for easy tracking of progress. This step achieves precise matching between employee skills development and job requirements, improving the efficiency of training resource utilization.

[0021] S4. Run the three-dimensional employee profile assessment model. Using basic employee information, performance appraisal information, and training participation information as input data, calculate the employee's assessment scores in the ability, attitude, and potential dimensions to construct a three-dimensional employee profile. Specifically, step S4 involves the operation of the three-dimensional employee profile assessment model and the construction of a three-dimensional profile. During implementation, multi-dimensional input data is first integrated. The capability dimension data is extracted from employee basic information and performance appraisal information, including: education level (20 points for high school and below, 40 points for associate's degree, 60 points for bachelor's degree, and 80 points for master's degree and above); professional matching degree (the degree to which the employee's major matches the job requirements, 50 points for a perfect match, 30 points for a partial match, and 10 points for a mismatch); years of service (5 points for each full year, up to a maximum of 30 points); and skills assessment score (the average score of the skills dimension in the most recent assessment, with a maximum score of 100). The attitude dimension data is extracted from the performance appraisal and attendance system, including: work completion rate (actual number of completed tasks / planned number of completed tasks, converted to a percentage with a maximum score of 100); on-time delivery rate (number of on-time delivered tasks / total number of tasks, converted to a percentage with a maximum score of 100); teamwork score (evaluated jointly by department colleagues and leaders, with a maximum score of 100); and attendance compliance rate (actual number of days worked / expected number of days worked). The three dimensions are weighted and calculated as follows: 1) Number of participants, with a percentage conversion out of 100 points; 2) Potential dimension data is extracted from training participation and career planning data, including training enrollment rate (number of enrollments / total number of optional training sessions, percentage conversion out of 100 points), improvement in training performance (difference between the scores of the two most recent training assessments, out of 50 points), and promotion intention (assigned through a career planning questionnaire: strong 50 points, average 30 points, no intention 10 points). The three dimensions are then weighted (ability 40%, attitude 35%, potential 25%) to obtain an evaluation score for each dimension (out of 100 points, 60 points or above is considered passing). The scores are then integrated with the core characteristics of each dimension (e.g., highlighting strengths in the ability dimension and indicators for improvement in the attitude dimension) to construct a comprehensive employee profile including "basic information + three-dimensional scores + feature annotations." This profile is updated quarterly based on the latest data and stored in a dedicated employee profile database. This step provides accurate personnel characteristic basis for talent pool division and talent allocation, avoiding the problem of the traditional singularity in employee evaluation.

[0022] S5 imports the human cost elasticity coefficient obtained in S2, the personalized skill growth path plan generated in S3, and the three-dimensional employee profile constructed in S4 into the talent pool dynamic operation and management platform. The platform integrates and analyzes the data, classifies the talent pool into levels, and determines the allocation priority of talents at different levels. Specifically, step S5 involves importing multi-model results and performing dynamic operation analysis of the talent pool. During implementation, the data format must first be standardized. This includes converting the job-level human resource cost elasticity coefficients from step S2 (associating them with corresponding employees), the personalized skill development path plans from step S3 (extracting skill improvement goals and stage progress), and the employee 3D profiles from step S4 (extracting three-dimensional scores and core characteristics) into JSON format. This data is then imported into the talent pool dynamic operation management platform via API, using the employee ID as the unique association key to ensure accurate matching of multiple data types for the same employee. After receiving the data, the platform initiates an integrated analysis algorithm, first classifying the data by job sequence (technical, management, operations, etc.) and job level, and then calculating the employee's comprehensive score (score = elasticity coefficient matching score + skill development progress score). The talent pool is structured with a score of 35% and an average profile score of 45%. The flexibility coefficient and suitability score are calculated based on the optimal range of fit between the coefficient and the job position. The progress score is calculated based on the current / planned progress. Talent pool levels are categorized based on comprehensive scores (A level: 85 points and above; B level: 65-84 points; C level: below 65 points). Real-time job vacancy data (job title, quantity, and onboarding time) is used to determine allocation priorities (A level candidates are prioritized for senior / core vacancies; B level candidates are prioritized for middle / key vacancies; C level candidates are prioritized for training). The platform updates data every two weeks (incorporating the latest performance evaluations and training progress data) and displays the talent pool level distribution and allocation priority ranking on a visual interface. This process enables dynamic matching of talent resources with job requirements, improving talent utilization efficiency.

[0023] S6, based on the analysis results of the talent pool dynamic operation management platform, combined with the job vacancy parameters, salary adjustment parameters and training resource allocation parameters for enterprise human resource management optimization, formulates an implementation plan for enterprise human resource management optimization, and feeds the implementation plan back to the enterprise human resource management department.

[0024] Specifically, step S6 involves the formulation and feedback of the enterprise's human resources management optimization implementation plan. During implementation, the analysis results from the talent pool platform are first extracted (including the distribution of talent at each level, allocation priority suggestions, and job vacancy matching results). Then, optimization parameters are retrieved from the enterprise's human resources management parameter database (job vacancy parameters: vacant job name, quantity, required skills, and on-the-job timeframe of 15-30 days; salary adjustment parameters: total adjustment budget as a percentage of monthly revenue of 2%-5%, with maximum adjustment ranges for each level: 10% for entry-level, 15% for middle management, and 20% for senior management; training resource allocation parameters: training budget, number of projects that can be conducted, and maximum capacity for a single training session of 50 people). Subsequently, parameter matching and plan formulation are performed. The personnel allocation plan selects suitable employees from the corresponding talent pool according to priority, clearly defining the allocated personnel, original positions, new positions, on-the-job time, and handover requirements to ensure a vacancy fill rate of over 90%. The salary adjustment plan... The adjustment ratio is determined by combining the elasticity coefficient of human resource costs (the adjustment ratio is reduced for positions with high elasticity coefficients and increased for those with low elasticity coefficients), and the list of personnel to be adjusted, the salaries before and after the adjustment, and the implementation time are clearly defined to ensure that the total amount does not exceed the budget; the training resource allocation plan prioritizes the allocation of resources to C-level talents and employees with large skill gaps, and clearly defines the training projects, participants, time, and assessment requirements to ensure that the resource utilization rate is above 85%; the three types of plans are integrated into a complete optimized implementation plan, which includes implementation steps, responsible departments (human resources department, business departments), time nodes (such as the deployment to be started within 7 days after the plan feedback), and acceptance criteria (such as the vacancy filling rate meeting the standard and the salary adjustment being compliant), and then fed back to the company's human resources management department and synchronized to the internal approval system. After approval, the implementation is initiated. This step transforms the data analysis results into actionable management actions, directly improving the efficiency and accuracy of the company's human resources management.

[0025] Preferably, the expression for the labor cost elasticity prediction model is: ,in, This represents the elasticity coefficient of labor costs. For the number of job types, For the first Weighting coefficients for job categories For the first The difference in labor costs between the current and previous periods for this type of job. For the first Previous period labor costs for similar positions For the first Average salary of this type of position in the previous period For the first The difference between the average salary of this type of job in the current period and the previous period. The influence coefficient of enterprise size. The historical human resource cost fluctuation index of the enterprise is used; the parameters for optimizing the enterprise's human resource management include the number of job types, job weight coefficient, enterprise size influence coefficient, and historical human resource cost fluctuation index.

[0026] Specifically, when implementing the labor cost elasticity forecasting model, the number of job types is determined based on the company's actual business structure. Typically, manufacturing companies use 8-12 types, and service companies use 5-8 types. The weight coefficient for job type i needs to be set based on its contribution to the company's revenue: 0.15-0.25 for core business positions and 0.05-0.1 for auxiliary positions, with a total weight coefficient of 1. The difference between the current and previous period's labor costs for job type i needs to be calculated by extracting labor cost data from the company's financial system for two consecutive accounting periods. The previous period's labor cost is directly taken from the previous accounting period. The total human resource cost for each position; the average salary of position i in the previous period is the arithmetic mean of the salaries of all employees in that position in the previous accounting period. The difference between the average salary in the current period and the average salary in the previous period is obtained by subtracting the average salary in the previous period from the average salary in the current period; the enterprise size impact coefficient is determined based on the total number of employees in the enterprise, with a value of 0.8-1.0 for less than 1,000 employees, 1.0-1.2 for 1,000-5,000 employees, and 1.2-1.4 for more than 5,000 employees; the enterprise historical human resource cost volatility index is calculated by the standard deviation of the enterprise's annual human resource cost growth rate over the past 3-5 years, with the growth rate data extracted from the enterprise's annual financial report. In the implementation process, the specific values ​​of each parameter are first determined according to the above requirements, and then substituted into the model for segmented calculation. First, the correlation value between the change in human resource cost and the change in salary for each type of position is calculated, then multiplied by the corresponding position weight coefficient and summed, and finally the product of the enterprise size impact coefficient and the historical volatility index is added to obtain the human resource cost elasticity coefficient for each position level. This coefficient is used to judge the sensitivity of the position's human resource cost to salary adjustments, providing data support for enterprises to formulate differentiated salary strategies.

[0027] Preferably, the expression for the skill development path planning model is: ,in, A comprehensive score for the skills development path. For the number of skill modules, For the first The importance coefficient of each skill module For the current employee The score for mastery of each skill module, For the first The training effectiveness coefficient corresponding to each skill module For employee participation The duration of training for each skill module, The parameters for optimizing enterprise human resource management include the number of skill modules, the importance coefficient of skill modules, the training effectiveness coefficient of skill modules, and the matching degree of job skill requirements.

[0028] Specifically, when implementing the skills development path planning model, the number of skills modules is determined based on the core requirements of the position. Technical positions typically have 4-6 modules, while management positions have 3-5. The importance coefficient of the j-th skill module is set according to the skill's impact on job performance, with key skills having a value of 0.2-0.3 and general skills having a value of 0.08-0.15. The sum of the importance coefficients of all modules is 1. An employee's current mastery level of the j-th skill module is assessed through a combination of theoretical and practical examinations, with a maximum score of 100. Below 60 points indicates no mastery, 60-89 points indicates basic mastery, and above 90 points indicates proficient mastery. The training effectiveness coefficient corresponding to the j-th skill module is... The value is determined based on the employee's skill improvement after similar training in the past. For improvement of more than 30%, the value is 0.9-1.0; for improvement of 15%-30%, the value is 0.7-0.89; and for improvement of less than 15%, the value is 0.5-0.69. The duration of the employee's participation in the training of the j-th skill module is calculated based on the actual training hours. The duration of a single training session is usually not less than 4 hours, and the cumulative duration must meet the training requirements of that skill module. The job skill requirement matching degree is calculated by the overlap between the employee's existing skill combination and the job skill requirements. For overlap of more than 80%, the value is 0.9-1.0; for overlap of 60%-80%, the value is 0.7-0.89; and for overlap of less than 60%, the value is 0.5-0.69. During implementation, first calculate the product of the importance coefficient and the mastery score of each skill module, add the product of the training effectiveness coefficient and the training duration of that module, then multiply the results of all modules together, and finally multiply by the square root of the job skill requirement matching degree to obtain the comprehensive score of the skill growth path. A score of 80 or above is the optimal path, 60-79 is a qualified path, and a score below 60 requires the path plan to be readjusted.

[0029] Preferably, the expression for the three-dimensional employee profile evaluation model is: ,in, Three-dimensional evaluation vector for employee profiling. , These are the weighting coefficients for the ability dimension, attitude dimension, and potential dimension, respectively. Scoring based on ability dimensions Rate the attitude dimension. Score based on potential dimension. These are the evaluation error correction values ​​for the three dimensions; the parameters for optimizing enterprise human resource management include the three-dimensional weight coefficients and the three-dimensional evaluation error correction values.

[0030] Specifically, when implementing the three-dimensional employee profile assessment model, the weighting coefficients for the competence, attitude, and potential dimensions are set according to the company's human resource management priorities. If the company focuses on improving employee competence, the weighting for the competence dimension can be 0.45-0.5, for the attitude dimension 0.3-0.35, and for the potential dimension 0.2-0.25. If the company focuses on potential development, the weighting for the potential dimension can be increased to 0.3-0.35. The competence dimension score is calculated by weighting education level, professional matching degree, years of work experience, and skills assessment scores, with a maximum score of 100 points. Education level accounts for 20%, professional matching degree accounts for 20%, and years of work experience accounts for 10%. Skills assessment accounts for 50% of the score; the attitude dimension score is calculated by weighting work completion rate, on-time delivery rate, teamwork score, and attendance compliance rate, with a maximum score of 100 points, and each indicator accounting for 30%, 25%, 25%, and 20% respectively; the potential dimension score is calculated by weighting training participation rate, improvement in training performance, and promotion intention, with a maximum score of 100 points, and each indicator accounting for 35%, 35%, and 30% respectively; the evaluation error correction value for the three dimensions is calculated based on the deviation between past evaluation results and actual performance, typically ranging from -5 to 5. If past evaluations are generally high, the correction value is negative; if they are generally low, the correction value is positive. In the implementation process, a three-dimensional weighted diagonal matrix is ​​first constructed, then matrix multiplication is performed with the three-dimensional score vector, and finally the error correction vector is added to obtain the three-dimensional evaluation vector of the employee profile. The scores of each dimension in the vector are used to intuitively present the employee's performance level in different dimensions, providing a basis for talent classification and job matching.

[0031] Preferably, the data integration and analysis of the talent pool dynamic operation management platform adopts the following model: ,in, To allocate priority scores to the talent pool As the weight of the elasticity coefficient of labor costs, As a weighted factor in the overall score of skills development path, Employee profiling: a three-dimensional evaluation vector weighting. This represents the current capacity coefficient of the talent pool. The urgency coefficient for job vacancies; the parameters for optimizing enterprise human resource management include different data weights, talent pool capacity coefficient, and job vacancy urgency coefficient.

[0032] Specifically, when implementing the data integration and analysis model of the talent pool dynamic operation management platform, the weight of the human resource cost elasticity coefficient is set according to the company's cost control needs. If the company focuses on cost control, the weight is 0.35-0.45; if it focuses more on talent quality, the weight is 0.2-0.3. The weight of the comprehensive score for skill development paths is related to the company's talent development strategy. Companies that focus on employee growth use a weight of 0.4-0.5, while companies that focus on current capabilities use a weight of 0.25-0.35. The weight of the three-dimensional evaluation vector for employee profiles needs to complement the weights of the previous two items. The sum of these three factors is 1. The current capacity coefficient of the talent pool is determined based on the ratio of the actual number of people in the talent pool to the rated capacity. A value of 0.8-0.9 is used for ratios below 80%, 0.9-1.0 for 80%-100%, and 1.0-1.1 for over 100%. The vacancy urgency coefficient is set according to the vacancy duration and impact. A value of 1.2-1.3 is used for vacancy durations exceeding 30 days and impacting core business, 1.0-1.1 for vacancy durations of 15-30 days, and 0.8-0.99 for vacancy durations below 15 days. During implementation, the product of the human resource cost elasticity coefficient, the comprehensive score of the skills development path, and the employee profile evaluation vector (three dimensions) with their corresponding weights is calculated and summed. This sum is then divided by the product of the current capacity coefficient of the talent pool and the vacancy urgency coefficient to obtain the talent pool allocation priority score. The scores are ranked from highest to lowest to determine the talent allocation order, ensuring that high-priority talent is matched with urgent and important vacancy positions first.

[0033] Preferably, the enterprise human resources management optimization implementation plan is formulated using the following model: ,in, To optimize the execution priority of the plan, To allocate priority scores and weights to the talent pool This is the salary adjustment range coefficient. Adjust the budget amount for salaries. For the allocation coefficient of training resources, The total amount of training resources; the parameters for optimizing enterprise human resource management include execution priority weight, salary adjustment range coefficient, salary adjustment budget amount, training resource allocation coefficient, and total amount of training resources.

[0034] Specifically, when implementing the enterprise's human resource management optimization execution plan model, the priority score weight for talent pool allocation is set according to the importance of matching job vacancies with talent. The score for matching core job vacancies is 0.4-0.5, and for ordinary positions it is 0.25-0.35. The salary adjustment coefficient is determined based on the enterprise's salary strategy and market salary levels. If the enterprise's salary level is more than 10% lower than the market average, the coefficient is 1.1-1.2; if it is at the market average, the coefficient is 1.0; and if it is higher than the market average, the coefficient is 0.8-0.99. The salary adjustment budget is drawn from the enterprise's annual financial budget. The calculation typically extracts 2%-5% of the company's annual revenue, with the specific amount determined based on the company's profitability. The training resource allocation coefficient is set according to the importance and urgency of the training project, with a value of 0.3-0.4 for core skills training and 0.15-0.25 for general skills training. The total training resources include the total training budget, the number of trainers, and the training venue capacity. The training budget typically accounts for 3%-8% of the total human resource cost. The number of trainers must meet the needs of conducting training projects simultaneously, and the venue capacity must ensure that each trainee has at least 1.5 square meters of space per session. During implementation, the product of the talent pool allocation priority score and its corresponding weight is calculated, plus the product of the salary adjustment range coefficient and the salary adjustment budget, and finally the product of the training resource allocation coefficient and the total training resources. This yields the optimization plan's execution priority. The plan is implemented from highest to lowest priority, ensuring that resources are prioritized for the most significant aspects of optimizing the company's human resource management.

[0035] Preferably, step S3 includes the following sub-steps: S31, extracting training participation information of employees for the past three assessment cycles from the data storage module, filtering out the types of training projects, training duration, and training assessment results that employees have participated in, and establishing an employee training information dataset; S32, collecting skill requirement standard data for different positions in the enterprise, including the types of skills required for the position, the mastery requirements of different skills, and the skill update cycle, forming a job skill requirement standard library; S33, matching the employee training information dataset with the job skill requirement standard library, identifying the gap between the skills currently mastered by employees and the skills required for the position, and determining the skill modules that need to be supplemented; S34, based on the skill modules that need to be supplemented, combined with the enterprise's existing training resources and skill update cycle, assigning corresponding training projects to employees, and generating personalized skill growth path plans arranged in chronological order.

[0036] Specifically, step S3 is implemented in several steps. S31 involves extracting employee training participation information from the data storage module for the past three assessment cycles. Assessment cycles are typically set quarterly, with each cycle lasting three months. The extracted data must include the type of training program (e.g., professional skills training, management skills training), training duration (calculated based on actual participation hours, with any fraction of an hour counted as a full hour), and training assessment scores (out of 100, with 60 or above considered passing). After extraction, the data is categorized and organized by employee ID to construct an employee training information dataset, ensuring that the completeness of each employee's training records is no less than 95%. S32 involves collecting skill requirement standards for each position within the company. This data must include the types of core skills required for each position (3-5 core skills are set for each position, determined based on job function), the required level of mastery for each core skill (divided into basic, proficient, and expert levels; basic level requires mastery of basic operations, proficient level requires independent completion of skill-related tasks, and expert level requires the ability to guide others), and the skill update cycle (6-12 months for technical positions, etc.). For management positions (updated every 12-24 months), the collected data is categorized by job number to form a job skill requirement standard library, which is updated every six months based on industry technology development and business adjustments. S33 matches employee training information datasets with the job skill requirement standard library. By comparing employees' existing skills (judged from training assessment results and training project types) with job requirements, skill gaps are identified, and necessary skill modules are determined. During the matching process, it is crucial to ensure consistent skill classification standards to avoid biased gap assessments due to classification differences. S34, based on the necessary skill modules, and considering the company's existing training resources (including available training projects, training schedules, and the number of trainers) and skill update cycles, corresponding training projects are assigned to employees. Training project allocation must follow the principle of "basic first, then advanced," and no more than two training projects are allocated per cycle to avoid excessive employee training burden. Finally, a personalized skill development path plan is generated, arranged chronologically. The plan must clearly define the implementation time, assessment requirements, and skill improvement goals for each training project.

[0037] Preferably, step S4 includes the following sub-steps: S41, based on the employee's basic information, extract data on the employee's education, professional background, years of service, and tenure in the position as the basic input data for the competency dimension assessment; S42, organize the employee's performance appraisal information for the past two years, and select data on work completion rate, on-time delivery rate, and teamwork scoring indicators as the core input data for the attitude dimension assessment; S43, analyze the employee's active registration rate for training, the foresight of training course selection, and the trend of improvement in assessment results to obtain data related to the employee's learning willingness and development potential as the calibration input data for the potential dimension assessment; S44, substitute the input data of the three dimensions into the three-dimensional employee profile assessment model, calculate the assessment scores for different dimensions, and construct a three-dimensional employee profile including competency, attitude, and potential dimension scores through vector integration.

[0038] Specifically, step S4 is implemented in stages. S41 extracts data based on basic employee information. Educational background needs to be differentiated into four levels: high school and below, associate degree, bachelor's degree, and master's degree and above. Professional background needs to record the alignment between the employee's major and the job requirements. Years of experience are calculated based on the employee's cumulative working time in the industry (accurate to the year), and tenure in the current position is calculated based on the employee's working time in the current position (accurate to the month). After extraction, the data is organized into the basic input data for competency assessment, ensuring that the data source is the employee's onboarding documents and records from the company's HR system. Data accuracy must reach 100%; S42 compiles employee performance appraisal information for the past two years, with an annual appraisal cycle of 12 months. The extracted work completion rate is calculated as "actual completed tasks / planned completed tasks × 100%" (result rounded to the nearest integer). The on-time delivery rate is calculated as "on-time delivered tasks / total tasks × 100%" (result rounded to the nearest integer). Team collaboration scores are jointly evaluated by department colleagues (40%) and direct supervisors (60%) (maximum score 100, result rounded to the nearest integer). This compiled data serves as the core input for attitude dimension assessment. Data must be reviewed and confirmed by the Human Resources Department to avoid subjective scoring bias; S43 analyzes employee training-related data. The training enrollment rate is calculated as "number of times actively enrolled in training / total number of available training sessions × 100%" (results are rounded to the nearest integer). The foresight of training course selection is determined by judging the degree of fit between the selected courses and the future skill requirements of the position (high, medium, and low fit correspond to different scores). The improvement trend of assessment results is calculated based on the change in the assessment results of the last three training sessions (improvement, stagnation, and decline correspond to different scores). After analysis, data related to employee potential is obtained as key input data for potential dimension assessment; S44 substitutes the input data of the three dimensions into the three-dimensional employee profile assessment model. When the model is calculated, it will calculate the assessment score of each dimension according to the preset weights (40% for ability dimension, 35% for attitude dimension, and 25% for potential dimension) (maximum score of 100 points, results are rounded to one decimal place). Then, through vector integration, the scores of the three dimensions are combined with the core characteristics of each dimension (such as the strengths of skills in the ability dimension and the areas for improvement in the attitude dimension) to construct a three-dimensional employee profile. The profile needs to be stored in a dedicated database and updated quarterly based on the latest data.

[0039] Preferably, step S5 includes the following sub-steps: S51, receiving the human cost elasticity coefficients for different job levels output by S2, normalizing the coefficients, establishing a human cost elasticity coefficient database and associating it with corresponding job information; S52, importing the personalized skill development path plan for each employee generated in step S3, extracting the skill improvement goals and training cycle calibration information from the plan, and constructing an employee skill development information database; S53, retrieving the employee three-dimensional profile formed in step S4, sorting it in descending order according to the ability dimension score, dividing it into three ability level ranges of high, medium, and low, and establishing an employee ability level classification database; S54, importing the data from the human cost elasticity coefficient database, the employee skill development information database, and the employee ability level classification database into the talent pool dynamic operation management platform, the platform integrating multi-database data through a data association algorithm, classifying the talent pool levels based on the integration results, and calculating the allocation priority of different levels of talent.

[0040] Specifically, step S5 is implemented in stages. S51 receives the labor cost elasticity coefficients for different job levels output from step S2. Job levels are divided into entry-level, middle-level, and senior-level. The elasticity coefficient values ​​typically range from 0.8 to 2.0. After receiving the coefficients, they are normalized (converting the values ​​to the 0-1 range; the processing formula is set according to industry-standard settings). After processing, a labor cost elasticity coefficient database is established. The database needs to be associated with the corresponding job name, number, and number of positions, ensuring a one-to-one correspondence between the elasticity coefficient for each job level and the job information. The database update frequency is the same as that of step S2. The calculation frequency remains consistent (once a month); S52 imports the personalized skill development path plan for employees generated in step S3. The plan must include key information such as employee ID, skill improvement goals (divided into short-term 1-3 months, medium-term 4-6 months, and long-term 7-12 months), and training cycle (start and end time of each training project). After importing, it is stored according to employee ID to build an employee skill development information database. The database needs to synchronize the execution progress of the plan in real time (such as whether the training has been completed and whether the assessment has been passed), with a synchronization frequency of once a week; S53 retrieves the employee 3D profile formed in step S4 and extracts... The ability dimension scores (out of 100) in the profile are sorted in descending order and divided into three ability level ranges: high (80 points and above), medium (60-79 points), and low (below 60 points). An employee ability level classification database is then established, recording the employee's ranking within each range. The ranking update frequency is consistent with the profile update frequency (quarterly). S54 imports data from the human resource cost elasticity coefficient database, the employee skills development information database, and the employee ability level classification database into the talent pool dynamic operation management platform. The platform then activates a data association algorithm (based on "Employee ID - Job Number"). The design of the "ability level" association logic enables the integration of data from multiple databases. After integration, the talent pool is divided into levels (A level 85 points and above, B level 65-84 points, and C level below 65 points) based on a comprehensive score of "human resource cost elasticity coefficient adaptability (the degree of fit between the coefficient and the optimal range of the position) + skill growth progress (the ratio of the current progress to the planned progress) + ability level" (out of 100 points). Then, the allocation priority of talents at each level is determined by combining the urgency of the job vacancy (urgent, general, non-urgent). The allocation priority results need to be displayed on the platform's visualization interface, and the displayed data is updated every two weeks.

[0041] The human resource cost elasticity prediction model in this invention is an algorithmic model used to accurately calculate the sensitivity of human resource costs at different job levels within an enterprise to factors such as salary adjustments and employee turnover. Its implementation requires first extracting key input data from the enterprise's personnel data storage module, including salary disbursement information (average monthly salary, salary adjustment range) for each job level over the past three years, job position information (number of employees, employee turnover rate), and historical human resource cost adjustment data for the past five years (total human resource costs, human resource costs as a percentage of revenue). After standardizing this data, different parameter weights are assigned according to job level (30% for entry-level, 40% for middle management, and 30% for senior management). This is then corrected by combining industry benchmark values ​​for human resource cost elasticity. The model then calculates and outputs the human resource cost elasticity coefficient for each job level (with a value range of 0.8-2.0). This model quantifies the changing patterns of human resource costs at different job levels, providing data support for companies to formulate salary adjustment plans. For example, job levels with high elasticity coefficients can appropriately reduce salary adjustments to control costs, while job levels with low elasticity coefficients can increase adjustments to retain talent. It breaks away from the traditional model of human resource cost forecasting that relies on experience-based judgment, improves the accuracy of cost forecasting, helps companies find a balance between controlling human resource costs and ensuring talent stability, optimizes the efficiency of human resource resource allocation, and provides financial-level personnel data support for the formulation of long-term business strategies.

[0042] The skills development path planning model in this invention is an algorithmic model that tailors skills enhancement plans for enterprise employees, aiming to achieve a precise match between employee skills development and job requirements. Its implementation requires first extracting training participation information (training project type, duration, and assessment results) from the employee's last two assessment cycles, as well as skills dimension scores from the last three performance appraisals. Simultaneously, it retrieves the core skill types (3-5 items), mastery requirements (basic, proficient, and expert levels), and skill update cycles (6-12 months for technical positions and 12-24 months for management positions) from the enterprise's job skills standard library for the corresponding positions. By comparing the gap between the employee's existing skills and job requirements, and considering the employee's skill improvement speed, the priority of skills enhancement is determined. Then, this data, along with the enterprise's existing training resources (available projects, time arrangements, and number of instructors), is input into the model. The model is divided into short-term (1-3 months), medium-term (4-6 months), and long-term (7-12 months) phases, assigning training projects and clarifying improvement goals for employees, thus generating personalized skills development path plans. This model provides each employee with a clear and actionable direction for skills enhancement, avoiding the blind investment of training resources. For example, basic training programs are prioritized for employees with significant skill gaps, while advanced training programs are assigned to employees who are close to the job requirements. This motivates employees to improve themselves, enhances the fit between their skills and their positions, reduces the problem of insufficient job competence caused by skill mismatch, and improves the utilization efficiency of corporate training resources. It also helps the company cultivate a professional talent pool that meets the needs of business development and enhances the company's core competitiveness.

[0043] The three-dimensional employee profile assessment model in this invention is an algorithm model that comprehensively portrays employee characteristics from three dimensions: ability, attitude, and potential, and is used to achieve a three-dimensional and multi-dimensional evaluation of employees. In fact, this requires integrating data from multiple sources as input. The competency dimension data includes employee education (high school and below 20 points, junior college 40 points, bachelor's degree 60 points, master's degree and above 80 points), professional matching degree (perfect match 50 points, partial match 30 points, mismatch 10 points), years of service (5 points for each full year, up to a maximum of 30 points), and skills assessment score (out of 100). The attitude dimension data includes work completion rate, on-time delivery rate, teamwork score, and attendance compliance rate (all converted to a percentage and out of 100). The potential dimension data includes training enrollment rate, improvement in training performance, and promotion intention (assigned according to corresponding standards). The three dimensions are weighted according to preset weights (competency 40%, attitude 35%, potential 25%) to obtain the evaluation score for each dimension (out of 100). The scores are then integrated with the core characteristics of each dimension (strengths and areas for improvement) to construct a three-dimensional employee profile, which is updated quarterly based on the latest data. This model provides enterprises with a comprehensive and objective basis for employee evaluation, avoiding the limitations of traditional single-dimensional evaluation. For example, it can judge an employee's current job competency through the ability dimension and judge an employee's future development space through the potential dimension. It helps enterprises accurately identify different types of talents, providing scientific support for talent selection, job allocation, and promotion decisions, and achieving "precise matching of people and jobs". At the same time, it allows employees to clearly understand their own strengths and weaknesses, clarify their development direction, enhance employees' sense of belonging and work enthusiasm, and promote the common development of enterprises and employees.

[0044] The talent pool dynamic operation and management platform of this invention is a digital platform that integrates the output results of multiple models to achieve dynamic talent management and efficient allocation. It is the core hub connecting employee data and human resource management decisions. It first imports the job level elasticity coefficients output by the human resource cost elasticity prediction model, the personalized employee growth plans generated by the skill growth path planning model, and the three-dimensional employee profile constructed by the employee profile three-dimensional evaluation model into the platform via API interface in a unified data format (JSON format). The platform uses the employee ID as the unique association key to achieve accurate matching of multiple types of data. The platform then activates a multi-dimensional data integration algorithm to classify employee data by job sequence (technical, management, operations, etc.) and level, calculating the employee's comprehensive score (elasticity coefficient matching score 20% + skill growth progress score 35% + profile average score 45%). Based on the score, the platform classifies the talent pool into levels (Level A: 85 points or above, Level B: 65-84 points, Level C: below 65 points). Then, it combines this with the company's real-time job vacancy data (vacancy job name, quantity, and arrival time) to determine the allocation priority. The data is updated every two weeks and displayed on a visual interface. This platform enables dynamic matching of talent resources with job requirements, improving the efficiency of talent allocation. For example, it prioritizes the allocation of A-level talents to senior or core positions, and prioritizes skills enhancement training for C-level talents. It breaks down information silos within enterprises, achieves centralized management and efficient utilization of talent resources, reduces resource waste caused by talent mismatch, and allows enterprises to grasp their internal talent structure and reserves in real time. This provides rapid and accurate talent support for enterprises to cope with business expansion, job vacancies, and other situations, ensuring the flexibility and dynamic adaptability of enterprise human resource management.

[0045] like Figure 2As shown, this is an enterprise human resources management optimization system based on big data statistical analysis. The system applies a method for optimizing enterprise human resources management based on big data statistical analysis, and includes: a multi-source human resources data collection and classification storage unit, which collects basic employee information, job information, salary payment information, performance appraisal information, and training participation information, classifies and stores the collected information, and establishes a data transmission connection with the subsequent data processing unit to send the classified human resources data to the data processing unit; a human resources cost elasticity prediction and calculation unit, which receives salary payment information, job information, and historical human resources cost adjustment data transmitted from the multi-source human resources data collection and classification storage unit, calls a preset human resources cost elasticity prediction model to perform calculations, generates human resources cost elasticity coefficients for different job levels, and transmits the coefficients to the talent pool dynamic operation unit; and an employee skills development path planning and generation unit, which obtains employee training participation information, performance appraisal information, and job skill requirement standard data from the multi-source human resources data collection and classification storage unit, processes it through a skills development path planning model to generate personalized skills development path plans, and sends the plans to the talent pool dynamic operation unit; The employee three-dimensional profile construction and evaluation unit receives basic employee information, performance appraisal information, and training participation information from the multi-source data collection and classification storage unit. It then runs the employee profile three-dimensional evaluation model to calculate evaluation scores for different dimensions, constructs a three-dimensional employee profile, and transmits it to the talent pool dynamic operation unit. The talent pool dynamic operation and data analysis unit establishes data receiving connections with the human resource cost elasticity prediction and calculation unit, the employee skill development path planning and generation unit, and the employee three-dimensional profile construction and evaluation unit. It integrates and analyzes the received human resource cost elasticity coefficient, skill development path plan, and employee three-dimensional profile, classifies the talent pool into levels, determines allocation priorities, and interacts with the human resource management optimization plan formulation unit. The human resource management optimization plan formulation and feedback unit receives the analysis results output by the talent pool dynamic operation and data analysis unit. Combining these with the enterprise's human resource management optimization parameters such as job vacancy parameters, salary adjustment parameters, and training resource allocation parameters, it formulates an optimization implementation plan and feeds it back to the enterprise's human resource management department. This unit maintains real-time data communication with the talent pool dynamic operation and data analysis unit to ensure the timeliness of the plan formulation.

[0046] The enterprise HR management optimization methods and systems based on big data statistical analysis can achieve efficient integration and in-depth analysis of enterprise HR data. By classifying and storing various types of data such as basic employee information and job information, it provides comprehensive data support for subsequent model calculations, avoiding the lag and errors of manual data processing. It constructs a multi-dimensional model collaborative operation mechanism, using models such as human resource cost elasticity prediction, skills growth path planning, and three-dimensional employee profile assessment to output accurate cost elasticity coefficients, personalized growth plans, and three-dimensional employee profiles, providing a scientific basis for HR decisions. Relying on a dynamic talent pool operation and management platform, it achieves data linkage, integrates and analyzes the results of multiple models to classify talent pool levels, determine allocation priorities, and formulate optimization plans based on parameters such as job vacancies and salary adjustments, thereby improving the refinement and dynamic adaptability of HR management and promoting the rational allocation of talent resources.

[0047] This system addresses the problem of a lack of systematic models and reliance on simple extrapolation in human resource cost forecasting. It employs a human resource cost elasticity forecasting model that comprehensively incorporates key parameters such as changes in job level salaries, company size, and historical cost fluctuations. Through systematic calculations, it derives a cost elasticity coefficient that more closely reflects actual conditions, providing accurate references for corporate salary adjustments and replacing traditional experience-based judgments. Addressing the disconnect between employee development planning and talent pool management, it utilizes a skills growth path planning model to link training effectiveness with job skill requirements. A three-dimensional employee profiling assessment model comprehensively presents employee capabilities, attitudes, and potential. Furthermore, a dynamic talent pool operation and management platform integrates multi-dimensional data, achieving deep linkage between employee development planning and talent pool level classification and allocation, thus solving the problem of inefficient talent resource allocation.

[0048] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," "link," and "fix" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0049] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing enterprise human resource management based on big data statistical analysis, characterized in that: Includes the following steps: S1. Collect internal personnel data, including employee basic information, job information, salary payment information, performance appraisal information, and training participation information. Transmit the collected personnel data to the data storage module for categorized storage. S2. Invoke the human resource cost elasticity prediction model. Input the stored salary payment information, job information, and historical human resource cost adjustment data. Calculate the human resource cost elasticity coefficients for different job levels using the model. S3. Activate the skills development path planning model. Import employee training participation information, performance appraisal information, and job skill requirement standard data. Process the data using the model to generate a personalized skills development path plan for each employee. S4. Run the three-dimensional employee profile assessment model, using basic employee information, performance appraisal information, and training participation information as input data, to calculate the employee's assessment scores in the ability, attitude, and potential dimensions, thus constructing a three-dimensional employee profile. S5. Import the human resource cost elasticity coefficient obtained in S2, the personalized skills development path plan generated in S3, and the three-dimensional employee profile constructed in S4 into the talent pool dynamic operation management platform. The platform integrates and analyzes the data, classifies the talent pool into levels, and determines the allocation priority for different levels of talent. S6. Based on the analysis results of the talent pool dynamic operation management platform, combined with the enterprise's HR management optimization parameters for job vacancy, salary adjustment, and training resource allocation, formulate an enterprise HR management optimization implementation plan, and feed the implementation plan back to the enterprise's HR management department.

2. The enterprise personnel management optimization method based on big data statistical analysis according to claim 1, characterized in that, The expression for the labor cost elasticity prediction model is as follows: ,in, This represents the elasticity coefficient of labor costs. For the number of job types, For the first Weighting coefficients for job categories For the first The difference in labor costs between the current and previous periods for this type of job. For the first Previous period labor costs for similar positions For the first Average salary of this type of position in the previous period For the first The difference between the average salary of this type of job in the current period and the previous period. The influence coefficient of enterprise size. The historical human resource cost fluctuation index of the enterprise is used; the parameters for optimizing the enterprise's human resource management include the number of job types, job weight coefficient, enterprise size influence coefficient, and historical human resource cost fluctuation index.

3. The enterprise personnel management optimization method based on big data statistical analysis according to claim 1, characterized in that, The expression for the skill development path planning model is: ,in, A comprehensive score for the skills development path. For the number of skill modules, For the first The importance coefficient of each skill module For the current employee The score for mastery of each skill module, For the first The training effectiveness coefficient corresponding to each skill module For employee participation The duration of training for each skill module, The parameters for optimizing enterprise human resource management include the number of skill modules, the importance coefficient of skill modules, the training effectiveness coefficient of skill modules, and the matching degree of job skill requirements.

4. The enterprise personnel management optimization method based on big data statistical analysis according to claim 1, characterized in that, The expression for the three-dimensional employee profile assessment model is as follows: ,in, Three-dimensional evaluation vector for employee profiling. , These are the weighting coefficients for the ability dimension, attitude dimension, and potential dimension, respectively. Scoring based on ability dimensions Rate the attitude dimension. Score based on potential dimension. These are the evaluation error correction values ​​for the three dimensions; the parameters for optimizing enterprise human resource management include the three-dimensional weight coefficients and the three-dimensional evaluation error correction values.

5. The enterprise personnel management optimization method based on big data statistical analysis according to claim 1, characterized in that, The data integration and analysis of the talent pool dynamic operation and management platform adopts the following model: ,in, To allocate priority scores to the talent pool As the weight of the elasticity coefficient of labor costs, As a weighted score for the overall skill development path, Employee profiling is a three-dimensional assessment vector weighting. This represents the current capacity coefficient of the talent pool. The urgency coefficient for job vacancies; the parameters for optimizing enterprise human resource management include different data weights, talent pool capacity coefficient, and job vacancy urgency coefficient.

6. The enterprise personnel management optimization method based on big data statistical analysis according to claim 1, characterized in that, The model used in formulating the enterprise human resources management optimization implementation plan is as follows: ,in, To optimize the execution priority of the plan, To allocate priority scores and weights to the talent pool This is the salary adjustment range coefficient. Adjust the budget amount for salaries. For the allocation coefficient of training resources, The total amount of training resources; the parameters for optimizing enterprise human resource management include execution priority weight, salary adjustment range coefficient, salary adjustment budget amount, training resource allocation coefficient, and total amount of training resources.

7. The enterprise personnel management optimization method based on big data statistical analysis according to claim 1, characterized in that, S3 includes the following steps: S31, extracting employee training participation information from the data storage module for the past three assessment cycles, filtering out the types of training projects employees have participated in, training duration, and training assessment results, and establishing an employee training information dataset; S32, collecting skill requirement standard data for different positions within the company, including the types of skills required for each position, the required level of mastery for different skills, and the skill update cycle, forming a job skill requirement standard library; S33, matching the employee training information dataset with the job skill requirement standard library, identifying the gap between the skills currently mastered by employees and the skills required for the position, and determining the skill modules that need to be supplemented; S34, based on the skill modules that need to be supplemented, combined with the company's existing training resources and skill update cycle, assigning corresponding training projects to employees, and generating personalized skill development path plans arranged in chronological order.

8. The enterprise personnel management optimization method based on big data statistical analysis according to claim 1, characterized in that, S4 includes the following steps: S41, based on the employee's basic information, extract data on the employee's education, professional background, years of service and tenure in the position as the basic input data for the ability dimension assessment. S42. Compile employee performance appraisal information from the past two years, and select data on work completion rate, on-time delivery rate, and teamwork rating as core input data for attitude dimension assessment; S43. Analyze employee participation in training, the foresight of training course selection, and the trend of performance improvement to obtain data related to employee learning willingness and development potential, which will serve as calibration input data for potential dimension assessment; S44. Substitute the input data from the three dimensions into the three-dimensional employee profile assessment model to calculate the assessment scores for different dimensions, and construct a three-dimensional employee profile including scores for ability, attitude, and potential dimensions through vector integration.

9. The enterprise personnel management optimization method based on big data statistical analysis according to claim 1, characterized in that, S5 includes the following steps: S51, receiving the human cost elasticity coefficients of different job levels output by S2, normalizing the coefficients, establishing a human cost elasticity coefficient database and associating it with the corresponding job information; S52, Import the personalized skill development path plan for each employee generated in step S3, extract the skill improvement goals and training cycle calibration information from the plan, and build an employee skill development information database; S53, Retrieve the employee three-dimensional profile formed in step S4, sort it in descending order according to the ability dimension score, divide it into three ability level ranges of high, medium and low, and establish an employee ability level classification database; S54, Import the data from the human resource cost elasticity coefficient database, the employee skill development information database and the employee ability level classification database into the talent pool dynamic operation management platform. The platform integrates data from multiple databases through data association algorithms, divides the talent pool into levels based on the integration results and calculates the allocation priority of talents of different levels.

10. An enterprise human resource management optimization system based on big data statistical analysis, characterized in that: This system is applied to the enterprise personnel management optimization method based on big data statistical analysis as described in claim 1, comprising: a personnel data multi-source collection and classification storage unit, which collects basic information of employees, job information, salary payment information, performance appraisal information, and training participation information within the enterprise, classifies and stores the collected information, and establishes a data transmission connection with the subsequent data processing unit to send the classified personnel data to the data processing unit; a human resource cost elasticity prediction and calculation unit, which receives salary payment information, job information, and historical human resource cost adjustment data transmitted by the personnel data multi-source collection and classification storage unit, calls a preset human resource cost elasticity prediction model to perform calculations, generates human resource cost elasticity coefficients for different job levels, and transmits the coefficients to the talent pool dynamic operation unit; an employee skill growth path planning and generation unit, which obtains employee training participation information, performance appraisal information, and job skill requirement standard data from the personnel data multi-source collection and classification storage unit, processes them through a skill growth path planning model to generate personalized skill growth path plans, and sends the plans to the talent pool dynamic operation unit; and a three-dimensional employee profile construction unit. The talent pool consists of three units: **Evaluation and Construction Unit:** This unit receives basic employee information, performance appraisal information, and training participation information from the multi-source data collection and classification storage unit. It then runs a three-dimensional employee profile evaluation model to calculate employee scores across different dimensions, constructing a comprehensive employee profile and transmitting it to the talent pool dynamic operation unit. **Talent Pool Dynamic Operation and Data Analysis Unit:** This unit establishes data receiving connections with the human resource cost elasticity prediction and calculation unit, the employee skill development path planning and generation unit, and the employee three-dimensional profile construction and evaluation unit. It integrates and analyzes the received human resource cost elasticity coefficients, skill development path plans, and employee profiles, classifying the talent pool into levels and determining allocation priorities. It also interacts with the human resource management optimization plan formulation unit. **Human Resource Management Optimization Plan Formulation and Feedback Unit:** This unit receives the analysis results from the talent pool dynamic operation and data analysis unit. Combining these with parameters related to job vacancy, salary adjustments, and training resource allocation for human resource management optimization, it formulates an optimization implementation plan and feeds it back to the company's human resource management department. This unit maintains real-time data communication with the talent pool dynamic operation and data analysis unit to ensure the timeliness of the plan formulation.

Images