Building enterprise project group human resource allocation system based on multi-objective optimization

Abstract

The invention relates to the technical field of human resource management methods, and discloses a building enterprise project group human resource configuration system based on multi-objective optimization, which comprises a model construction module used for constructing a multi-objective optimization model including maximization of project group overall man-post matching degree, optimization of team personnel age structure and minimization of human resource cost; the information acquisition module is used for acquiring employee information and post information; the matching degree quantification module is used for quantifying the post matching degree based on the post competency model and the personnel portrait, and evaluating the age structure rationality of the team personnel by using the personnel marginal contribution rate curve; and the scheme generation module is used for solving the multi-objective optimization model by adopting an improved NSGA-II algorithm to obtain a human resource allocation scheme and outputting the human resource allocation scheme. The invention aims to provide a multi-objective optimization system which can consider the man-post matching degree, the team age structure and the human resource cost at the same time, so as to improve the scientificity and effectiveness of human resource configuration of a building enterprise.

Description

Technical Field

[0001] The present invention relates to the technical field of human resource management methods, and particularly to a human resource allocation system for project groups of construction enterprises based on multi-objective optimization. Background Art

[0002] As one of the most critical production factors in construction enterprises, the rational allocation of human resources is directly related to the operation efficiency of the enterprise and the success rate of projects. Especially in the project group management of large construction enterprises, due to multiple projects being carried out simultaneously, the problem of human resource allocation becomes more complex, posing higher requirements for the enterprise's management ability.

[0003] Currently, construction enterprises generally have the following problems in the human resource allocation system: Low efficiency of human resource allocation: Traditional human resource allocation systems mostly rely on empirical judgment and manual analysis modules, lacking scientific quantitative index processing units and systematic optimization algorithm modules. Project managers usually allocate personnel based on subjective experience or simple qualification matching, resulting in low person-job matching degree and serious resource waste.

[0004] Lack of comprehensive consideration of multiple objectives: Existing human resource allocation systems often only contain single-objective processing modules (such as cost minimization module or resource utilization maximization module), lacking a comprehensive processing module that can balance multiple objectives such as person-job matching degree, team structure optimization, and cost control, resulting in poor overall allocation effects.

[0005] Fierce competition for project group resources: In the project group management environment, each sub-project is carried out in parallel, and employees cannot be reused among different sub-projects, intensifying the competition for human resources. Existing systems lack an effective resource priority allocation module and cannot meet the differentiated needs of multiple projects.

[0006] Unreasonable team structure: Existing systems ignore the impact of the team personnel age structure assessment module on project performance, resulting in an overly aging or young team structure, which is not conducive to the overall performance of the team.

[0007] Low algorithm processing efficiency: For complex multi-objective optimization problems, the optimization algorithm processing modules in existing systems often have high computational complexity and low solution efficiency, making it difficult to meet the actual application requirements. Summary of the Invention

[0008] In order to solve the problems existing in the above-mentioned prior art, the present invention aims to provide a multi-objective optimization system that can simultaneously consider the person-job matching degree, team age structure, and human resource cost, and achieve rapid solution through an efficient algorithm to improve the scientificity and effectiveness of human resource allocation in construction enterprises.

[0009] To achieve the above-mentioned invention objectives, the technical solutions provided by the present invention include: A human resource allocation system for construction enterprise project groups based on multi-objective optimization, including: A model construction module, which is used to construct a multi-objective optimization model including maximizing the overall person-post matching degree of the project group, optimizing the age structure of the team members, and minimizing the human resource cost, and set the allocation constraints for employees and posts; An information acquisition module, which is signal-connected to the model construction module, and is used to acquire employee information and post information, and transmit the acquired information to the model construction module and the matching degree quantification module; A matching degree quantification module, which is signal-connected to the information acquisition module and the model construction module, and is used to receive the employee information and post information transmitted by the information acquisition module, quantify the person-post matching degree based on the post competency model and the personnel portrait, and evaluate the rationality of the age structure of the team members by using the employee marginal contribution rate curve, and transmit the quantification result signal to the model construction module and the solution generation module; A solution generation module, which is signal-connected to the model construction module and the matching degree quantification module, and is used to receive the multi-objective optimization model transmitted by the model construction module and the quantification result signal transmitted by the matching degree quantification module, solve the multi-objective optimization model by using the improved NSGA-II algorithm, obtain the human resource allocation solution and output it.

[0010] Preferably, the employee information includes the employee's skill level, work experience, educational background, performance, professional qualification certificate, and age information; the post information includes the duty requirements, skill requirements, experience requirements, educational requirements, qualification certificate requirements, and age structure requirements of the post.

[0011] Preferably, the matching degree quantification module includes: A competency model construction unit, which is used to construct the competency model of each post according to the post information and determine the weights of each competency index; A personnel portrait construction unit, which is used to construct the personnel portrait of the employee according to the employee information and quantify the scores of each competency index; A matching degree calculation unit, which is used to calculate the person-post matching degree score of each employee and each post based on the competency model of the post and the personnel portrait of the employee.

[0012] Preferably, the matching degree quantification module further includes an age structure evaluation unit, and this unit includes: A contribution rate curve fitting sub-unit, which is used to fit the employee marginal contribution rate curve based on the historical performance data and age information of the employee; A contribution level determination sub-unit, which is used to determine the expected contribution level of employees of different age groups according to the employee marginal contribution rate curve; A team contribution calculation subunit, configured to calculate the overall expected contribution of the team based on the age distribution of current team members and the expected contribution levels of employees in each age group. A structural rationality evaluation subunit, configured to compare the overall expected contribution of the team with the expected contribution under a preset reasonable age structure, and evaluate the rationality of the current team age structure.

[0013] Preferably, the method for the solution generation module to solve the multi-objective optimization model using the improved NSGA-II algorithm, obtain the human resource allocation solution and output it includes: S101. Perform double-layer segmented encoding on the chromosome, where the chromosome is used to represent both personnel-project assignment information and personnel-position assignment information; among them, the first-layer chromosome represents the project to which the personnel are assigned, and the second-layer chromosome represents the matching degree, expected salary and age between the personnel and the position. S102. Adopt non-dominated sorting based on the early rejection strategy to accelerate the sorting process of population individuals. S103. Perform individual selection based on the improved niche strategy, where the niche radius is dynamically determined according to the Euclidean distance between population individuals. S104. Perform crossover operation using the partially matched crossover operator to ensure the uniqueness of genes in the chromosome after crossover; perform single-point mutation operation on the chromosome and perform duplicate removal processing to ensure the uniqueness of genes in the chromosome after mutation. S105. Terminate the algorithm according to the number of iterations and the fitness value, and output the Pareto optimal solution set as the human resource allocation solution.

[0014] Preferably, the assignment constraints for employees and positions set by the model construction module include: Each employee can be assigned to at most one position, and at the same time, it is allowed that some employees are not assigned. Each position must be assigned an employee. Set a priority weight coefficient for each project, where the priority weight coefficient is a value between 0 and 1, and the sum of the priority weight coefficients of all projects is 1.

[0015] Preferably, the objective function of the multi-objective optimization model constructed by the model construction module includes: S201. Maximize the overall personnel-position matching degree of the project group , expressed as: ; Among them, represents the function of maximizing the overall personnel-position matching degree of the project group of, represents the priority weight coefficient of project h, N is the total number of projects, n is the personnel number, and m is the position number. Indicates the job matching degree between job j of project h and the job of person i; Is a 0-1 variable. When the value is 1, it indicates that person i has been arranged to hold job j; S202. Optimize the age structure of the team members , which is expressed as: ; Among them, Indicates the function to maximize the age structure of the team members of the function, Indicates the rationality evaluation value of the age structure of the team members of project h; S203. Minimize the human resource cost , which is expressed as: ; Among them, Indicates the function to minimize the human resource cost of the function, Indicates the expected salary of person i for job j.

[0016] Preferably, the method for individual selection based on the improved niche strategy includes: S301. Calculate the Euclidean distance between individuals in the population: ; Among them, x and y represent two random individuals in the population, Indicates the Euclidean distance between x and y, and xᵢ and yᵢ are the values of the i-th objective function corresponding to individual x and individual y respectively; S302. After calculating the Euclidean distance between each individual and other individuals, take the average value of the minimum Euclidean distance values of all individuals as the initial value of the niche radius; S303. Dynamically iterate and dynamically adjust the niche radius. The niche radius gradually decreases according to the following formula: ; Indicates the current niche radius, is a constant; gs is the current iteration number, and gs max is the maximum iteration number; S304. When the Euclidean distance between two individuals x and y is less than the current niche radius , compare the fitness values of these two individuals, and punish the individual with the lower fitness value to reduce its probability of being selected.

[0017] Preferably, the calculation process of the job matching degree includes the following sub-steps: S401. Analyze the job attributes, judge the competency requirements of the employees needed for the job, record the set of jobs that require personnel in the project as J, and the set of available personnel for each job as I; S402. Obtain the matching results of person i and job j on the t-th qualification factor respectively , the matching results of person i and job j on the s-th ability factor , and the competency evaluation value of person i on job j ; S403. Based on the above evaluation results, calculate the job matching degree of person i on job j : ; Among them, is a piecewise function and ; Q is the penalty coefficient, is the weight of the ability factor.

[0018] Beneficial effects 1. Improve the accuracy of person-job matching: Through the competency model construction unit and the personnel portrait construction unit in the matching degree quantification module of this system, the system realizes the precise quantification and matching of employees' abilities and job requirements, overcomes the subjectivity and arbitrariness of relying on experience judgment in traditional systems, and makes personnel allocation more scientific and reasonable. Specifically, the matching degree calculation unit of this system takes into account both the basic condition assessment of the job and the comprehensive assessment of competency, and ensures that the basic conditions are preferentially met through a piecewise function and a penalty mechanism, greatly improving the accuracy of person-job matching.

[0019] 2. Achieve multi-objective collaborative optimization: The multi-objective optimization model of person-job matching - team personnel age structure - salary expenditure constructed by the model construction module of this system breaks through the limitations of traditional single-objective optimization systems and realizes multi-objective collaborative optimization. By setting different priority weight coefficients for the project, the pertinence and flexibility of resource allocation are further improved, enabling the enterprise to adjust the resource allocation strategy according to actual needs.

[0020] 3. Improve the algorithm solving efficiency: The solution generation module of this system adopts the NSGA-II algorithm improved based on multiple strategies. Through the early rejection strategy of the sorting acceleration unit and the improved niche strategy of the individual selection unit, the algorithm solving speed and result quality are significantly improved. The double-layer segmented coding method of the chromosome coding unit enables the system to represent the allocation relationships of personnel-project and personnel-job simultaneously. The partially matched crossover and single-point mutation operations of the crossover mutation unit ensure the effectiveness of the solution, enabling the optimization result to better guide the actual human resource allocation decision.

[0021] 4. Reduce human resource costs: Through the unit of minimizing human resource costs in the model construction module, this system effectively controls the human resource costs of enterprises. Practical application cases show that compared with traditional manual allocation systems, this system can significantly reduce the human resource expenditure of enterprises and improve the economic efficiency of enterprises on the premise of ensuring the matching degree of personnel and positions and a reasonable team structure.

[0022] 5. Improve project management efficiency: This system improves the efficiency and scientificity of human resource allocation in the project portfolio of construction enterprises, reduces the time and errors of manual decision-making, and makes project management more efficient. In practical applications, this system can quickly generate multiple alternative allocation plans for decision-makers to choose from, greatly improving the flexibility and scientificity of decision-making. Brief Description of the Drawings

[0023] Figure 1 It is a schematic structural diagram of a human resource allocation system for construction enterprise project portfolios provided in a preferred embodiment of the present invention. Detailed Embodiment

[0024] As Figure 1 shown, this embodiment provides a human resource allocation system for construction enterprise project portfolios based on multi-objective optimization, including a model construction module, an information acquisition module, a matching degree quantification module, and a plan generation module. Information transmission and functional collaboration are achieved through signal connections between the modules.

[0025] The model construction module is used to construct a multi-objective optimization model that includes maximizing the overall personnel-position matching degree of the project portfolio, optimizing the age structure of team members, and minimizing human resource costs, and set the allocation constraints for employees and positions. In the management of construction enterprise project portfolios, human resource allocation needs to consider multiple-dimensional goals simultaneously. This module first determines three core objective function units: the unit of maximizing the overall personnel-position matching degree of the project portfolio, the unit of optimizing the age structure of team members, and the unit of minimizing human resource costs. These three objective function units evaluate human resource allocation from multiple dimensions in terms of allocation efficiency, team structure, and economic cost. In some preferred embodiments, the specific objective functions of the multi-objective optimization model constructed by the model construction module include: S201. Maximize the overall personnel-position matching degree of the project portfolio , expressed as: ; Among them, represents the function of maximizing the overall personnel-position matching degree of the project portfolio , represents the priority weight coefficient of project h, N is the total number of projects, n is the personnel number, and m is the position number; represents the position matching degree between position j of project h and person i; is a 0-1 variable. When its value is 1, it means that employee i has been assigned to position j. S202. Optimize the age structure of the team members , which is expressed as: ; Among them, represents the function of maximizing the age structure of the team members of the team, represents the rationality evaluation value of the age structure of the team members for project h. Specifically, the rationality evaluation value of the age structure of the team members is calculated by the age structure evaluation unit of the matching degree quantification module. The age structure evaluation unit includes: The contribution rate curve fitting subunit is used to fit the marginal contribution rate curve of employees based on the historical performance data and age information of the employees; The contribution level determination subunit is used to determine the expected contribution level of employees in different age groups according to the marginal contribution rate curve of the employees; The team contribution calculation subunit is used to calculate the overall expected contribution of the team based on the age distribution of the current team members and the expected contribution level of employees in each age group; The structural rationality evaluation subunit is used to compare the overall expected contribution of the team with the expected contribution under the preset reasonable age structure, and evaluate the rationality of the current team age structure.

[0026] S203. Minimize the human resource cost , which is expressed as: ; Among them, represents the function of minimizing the human resource cost of the team, represents the expected salary of employee i for position j.

[0027] At the same time, to ensure the rationality of resource allocation, the model construction module also sets the allocation constraints for employees and positions, specifically including: each employee can be assigned to at most one position, and at the same time, it is allowed that some employees are not assigned to reflect the flexible deployment requirements in actual work; each position must be assigned an employee to ensure the basic operation needs of the project; set the priority weight coefficient for each project, and the priority weight coefficient is a value between 0 and 1, and the sum of the priority weight coefficients of all projects is 1, so that projects with higher priorities can obtain more high-quality resources. Through the construction of this multi-objective model, it is possible to effectively balance the three key objectives of person-position matching, team structure, and cost control, and provide a clear mathematical model signal basis for the solution generation module.

[0028] An information acquisition module, which is signal-connected to the model construction module, is used to acquire employee information and position information, and transmit the acquired information to the model construction module and the matching degree quantification module. This module is the data foundation for system implementation. Through various information channels such as connecting to the enterprise human resource management system interface, reading the employee resume database, integrating the performance evaluation record system, and collecting department demand research data, it comprehensively collects and organizes the relevant information of employees and positions.

[0029] The employee information collected by the information acquisition module mainly includes basic data such as professional skills, work experience, educational background, performance performance, professional qualification certificates, and age. The position information includes key elements such as job responsibilities, required skills, experience requirements, educational requirements, and qualification certificate requirements. These detailed employee and position information constitute the data foundation for evaluating the matching degree of people and positions and the rationality of the team age structure, providing necessary signal input support for the calculation and processing of the subsequent matching degree quantification module and the optimization decision of the solution generation module.

[0030] In some preferred embodiments, the employee information collected by the information acquisition module can be further divided into more detailed dimensions such as working years, project types, project scales, and roles played. The position information can further include more refined feature descriptions such as the specific content of job responsibilities, the importance of various skills, and the ideal age structure requirements. The information acquisition module transmits these complete information to other modules of the system through the signal interface to ensure the data integrity and accuracy of system operation.

[0031] A matching degree quantification module, which is signal-connected to the information acquisition module and the model construction module, is used to receive the employee information and position information transmitted by the information acquisition module, quantify the matching degree of people and positions based on the job competency model and the personnel portrait, and evaluate the rationality of the team personnel age structure using the employee marginal contribution rate curve, and transmit the quantification result signal to the model construction module and the solution generation module.

[0032] In some preferred embodiments, this module includes a competency model construction unit, a personnel portrait construction unit, and a matching degree calculation unit. The competency model construction unit receives the position information signal transmitted by the information acquisition module, constructs the competency model for each position, and determines the weights of each competency index; the personnel portrait construction unit receives the employee information signal transmitted by the information acquisition module, constructs the personnel portrait of the employee, and quantifies the scores of each competency index; the matching degree calculation unit calculates the matching degree score of each employee and each position based on the signals output by the competency model construction unit and the personnel portrait construction unit.

[0033] The matching degree quantification module further includes an age structure evaluation unit, which evaluates the rationality of the age structure of the team members through the collaborative work of a series of subunits. Specifically, the contribution rate curve fitting subunit fits the marginal contribution rate curve of employees based on the historical performance data and age information of the employees; the contribution level determination subunit determines the expected contribution level of employees in different age groups according to the fitted marginal contribution rate curve of employees; the team contribution calculation subunit calculates the overall expected contribution of the team based on the age distribution of the current team members and the expected contribution level of employees in each age group; the structural rationality evaluation subunit compares the overall expected contribution of the team with the expected contribution under the preset reasonable age structure to evaluate the rationality of the current team age structure.

[0034] These functional units convert the qualitative personnel and post information into quantitative index signals, providing accurate input parameters for the model construction module and the solution generation module. In some preferred embodiments, the quantification of the personnel-post matching degree in the matching degree calculation unit can be divided into two processing links: the basic condition evaluation of the post and the comprehensive evaluation of the ability and quality. Among them, the basic condition evaluation processing unit mainly examines whether the rigid requirements of the post are met, such as education background, certificates, etc., and the comprehensive evaluation processing unit of the ability and quality considers the matching degree between the employees in each ability dimension and the post requirements; the age structure evaluation unit can identify the best contribution age group as 31-40 years old by constructing an inverted U-shaped marginal contribution rate curve of employees, and evaluate the overall expected contribution value signal of the team accordingly.

[0035] The solution generation module, which is signal-connected to the model construction module and the matching degree quantification module, is used to receive the multi-objective optimization model transmitted by the model construction module and the quantification result signal transmitted by the matching degree quantification module, solve the multi-objective optimization model by using the improved NSGA-II algorithm, and obtain and output the human resource allocation solution.

[0036] This module is a key link in the system implementation. By improving the non-dominated sorting genetic algorithm (NSGA-II), it can efficiently solve the multi-objective optimization problem of the human resource allocation of the construction enterprise project group. The core idea of the improved NSGA-II algorithm is to maintain the population diversity through non-dominated sorting and crowding degree calculation, and at the same time evolve towards the Pareto optimal front. The implementation process of the algorithm includes main steps such as population initialization, fitness evaluation, non-dominated sorting, crossover and mutation, and elite strategy selection. Finally, a series of non-dominated solutions that balance the three objectives are output as optional human resource allocation solutions. In some preferred embodiments, the method for the solution generation module to solve the multi-objective optimization model by using the improved NSGA-II algorithm and obtain and output the human resource allocation solution includes: S101. Double-layer segment encoding is performed on the chromosome, and the chromosome is used to represent the personnel-project assignment information and the personnel-position assignment information simultaneously; wherein, the first-layer chromosome represents the projects assigned to the personnel, and the second-layer chromosome represents the matching degree between the personnel and the position, the expected salary, and the age. S102. Non-dominated sorting based on the early rejection strategy is adopted to accelerate the sorting process of the population individuals. S103. Individual selection is performed based on an improved niche strategy. Among them, the niche radius is dynamically determined according to the Euclidean distance between the population individuals. In some preferred embodiments, a method for individual selection based on an improved niche strategy is given, including: S301. Calculate the Euclidean distance between the individuals in the population: ; where x and y represent two random individuals in the population, represents the Euclidean distance between x and y, and xᵢ and yᵢ are the values of the i-th objective function corresponding to the individual x and the individual y respectively; different from the traditional genetic algorithm that only focuses on the individual fitness value, the present invention can comprehensively consider the distribution of individuals in multiple objective dimensions by calculating the Euclidean distance, providing an objective basis for the subsequent formation of niches. In actual implementation, to improve the calculation efficiency, a spatial index data structure such as a K-D tree can be used to accelerate the distance calculation process. When the population size is large, this optimization can reduce the time complexity of distance calculation.

[0037] S302. After calculating the Euclidean distance between each individual and other individuals, take the average value of the minimum Euclidean distance values of all individuals as the initial value of the niche radius; compared with the commonly used fixed radius in the prior art, the adaptive initial radius strategy can improve the convergence speed and increase the number of optimal solutions searched.

[0038] S303. Dynamically iterate and dynamically adjust the niche radius. The niche radius gradually decreases according to the following formula: ; represents the current niche radius, is a constant; gs is the current iteration number, and gs max is the maximum iteration number; the core idea of this step is that as the optimization process progresses, the niche radius is gradually reduced to achieve a natural transition from global exploration to local fine search. In the initial stage of iteration, a larger niche radius is beneficial to maintaining population diversity and promoting extensive exploration of the solution space; while in the later stage of iteration, the niche radius decreases, and the algorithm focuses more on the fine search of the promising region to improve the quality of the solution. controls the rate of radius contraction. The larger the β value, the faster the radius contracts; conversely, the slower the contraction. In some preferred embodiments, Take a value between 0.2 and 0.8.

[0039] S304. When the Euclidean distance between two individuals x and y is less than the current niche radius compare the fitness values of these two individuals and penalize the individual with the lower fitness value to reduce its probability of being selected. This distance-based penalty mechanism stems from the "competitive exclusion principle" in biological evolution, that is, there is resource competition among similar individuals, which will lead to the elimination of individuals with weaker adaptability. In multi-objective optimization problems, this mechanism helps to maintain population diversity, prevent individuals from over-aggregating in the same area, and thus effectively avoid the algorithm falling into local optimal solutions.

[0040] S104. Perform crossover operations using the partially mapped crossover operator to ensure the uniqueness of genes in the chromosomes after crossover; perform single-point mutation operations on the chromosomes and remove duplicates to ensure the uniqueness of genes in the mutated chromosomes; S105. Terminate the algorithm according to the number of iterations and fitness values, and output the Pareto optimal solution set as the human resource allocation plan.

[0041] It should be understood that the employee information and job information provided by the information acquisition module provide a data basis for the accurate calculation of the matching degree quantification module, enabling the enterprise to make personnel allocation decisions based on objective data rather than subjective experience, thereby greatly improving the scientificity and accuracy of human resource allocation. Employee information is a comprehensive description of the enterprise's existing human resources, including six key dimensions. The skill level refers to the evaluation results of an employee's ability level in a specific professional field, usually obtained through the enterprise's internal skill assessment system or professional examinations, including professional and technical capabilities, management capabilities, communication and coordination capabilities, etc., and is represented using a quantitative scoring system (such as a 1-5 scale); work experience includes not only the total working years of the employee, but also project experience in specific fields of the construction industry, such as project type, scale, and complexity, as well as the specific roles and responsibilities assumed, and this information is usually obtained from the employee's resume and historical project records; educational background refers to the employee's highest education level, major, and continuing education situation, reflecting the employee's knowledge base and learning ability; performance performance is the evaluation result of the employee's work performance based on the enterprise's annual performance assessment system, including performance in aspects such as work quality, work efficiency, innovation ability, and teamwork; professional qualification certificates refer to various professional qualification certificates held by the employee related to the construction industry, such as registered constructors, registered structural engineers, etc., including certificate type, level, and expiration date; age information directly reflects the actual age of the employee and is the basic data for evaluating the rationality of the team's age structure. This employee information is collected and sorted through channels such as the enterprise's human resource management system, employee files, performance assessment systems, and professional skill assessment platforms to form a comprehensive portrait of the employee.

[0042] Job information is a systematic description of the requirements for each job position in a construction enterprise project, also including six key dimensions. The responsibility requirements clarify the main job content, scope of powers and responsibilities, and job objectives of the position, which are the core content of the job definition; the skill requirements specify in detail the various professional skills required to be competent for the position and their minimum level requirements, such as design ability, construction management ability, budgeting ability, etc., usually using quantitative standards corresponding to the evaluation of employees' skill levels; the experience requirements stipulate the minimum working years required for the position and the experience requirements for specific types of projects, such as "requiring more than 5 years of experience in large public building project management"; the educational background requirements determine the minimum educational background required for the position, including the educational level and major requirements, such as "bachelor's degree or above in civil engineering or related majors"; the qualification certificate requirements list the list of professional qualification certificates required for the position, including the certificate type and level requirements; the age structure requirements consider the preferred age range of employees for the characteristics of the position. For example, senior management positions that require rich experience may prefer employees aged 35-45, while construction positions with higher physical requirements may be more suitable for employees aged 25-35. These job information are usually jointly determined by the project manager, human resources department and business department, formulated based on project characteristics, industry standards and the actual needs of the enterprise, and form a systematic job description.

[0043] In the present invention, the quantification calculation of the person-job matching degree and the evaluation of the rationality of the team age structure by the matching degree quantification module are the key links to achieve efficient human resource allocation. It should be understood that by evaluating the person-job matching degree and the rationality of the team age structure through scientific quantification methods, the traditional personnel allocation relying on subjective judgment can be transformed into an optimized decision based on objective data, thus significantly improving the allocation efficiency and allocation quality. The system's matching degree quantification module includes the following functional units and signal processing processes: The competency model construction unit constructs the competency models for each position according to the received position information signals and determines the weights of each competency indicator. Its signal processing process includes: First, based on the received position information signals, through the data processing algorithms of the expert interview method and the critical incident method, identify the core competency indicators for each position, usually including indicators such as professional knowledge, professional skills, work experience, management ability, communication and coordination ability, problem-solving ability, innovation ability, etc.; Second, use the mathematical processing unit of the analytic hierarchy process to determine the weights of each competency indicator, that is, construct a judgment matrix, determine the relative importance between indicators through expert scoring signals, calculate the eigenvector and conduct a consistency test, and finally obtain the weight value signals of each indicator; Finally, establish position competency standards, set scoring standards for each indicator (usually using a 1-5 point system), for example, for the "project management experience" indicator, it can be set as "5 points: more than 10 years of large project management experience; 4 points: 7-10 years of project management experience; 3 points: 4-6 years of project management experience; 2 points: 1-3 years of project management experience; 1 point: less than 1 year of project management experience". Through this signal processing method, a complete position competency model signal including an indicator system, a weight system, and a scoring standard is established.

[0044] The personnel portrait construction unit constructs the personnel portraits of employees according to the received employee information signals and quantifies the scores of each competency indicator. First, integrate the data signals from the enterprise human resource management system, performance evaluation system, skills assessment platform, and employee files transmitted by the information acquisition module to establish a multi-dimensional information database for employees; Second, for each employee, extract the information items corresponding to the position competency indicators, such as professional qualification certificates, educational background, work experience, performance evaluations, etc.; Then, based on the preset quantification rules, convert the performance of employees on each competency indicator into standardized score signals. For example, for the "professional knowledge" indicator, it can be scored according to the employee's academic qualifications (Ph.D.: 5 points, master's: 4 points, bachelor's: 3 points, etc.) and the level of professional qualification certificates; for the "work experience" indicator, it can be quantified according to the working years and project experience. This process can be automatically completed through the data mining algorithm unit or combined with the input of manual evaluation signals, and finally form a complete employee competency portrait signal.

[0045] The matching degree calculation unit calculates the person-position matching degree scores of each employee and each position based on the signals output by the competency model construction unit and the personnel portrait construction unit. Use the weighted summation model processing unit to multiply the scores of employees on each competency indicator by the weight of the indicator on a specific position and then sum. The calculated person-position matching degree scores are usually between 0 and 5, and the higher the score, the better the matching degree. Finally, organize the matching degree scores of all employees and all positions into a person-position matching matrix signal and transmit it to the model construction module and the solution generation module as an important input signal for multi-objective optimization.

[0046] In some other preferred embodiments, a calculation process of the job matching degree is given, which specifically includes the following sub-steps: S401. Analyze the job attributes, judge the competency requirements of the employees for the job, record the set of jobs that require personnel in the project as J, and the set of available personnel for each job as I; S402. Obtain the matching results of person i and job j on the t-th qualification factor , and ; the matching results of person i and job j on the s-th ability factor , and the competency evaluation value of person i on job j ; S403. Based on the above evaluation results, calculate the job matching degree of person i on job j : ; Wherein, is a piecewise function and , indicating that when a person meets the basic job qualification standards, the competency evaluation value and the comprehensive evaluation results based on the job competency model will be included in the MD calculation scope, otherwise its MD value will be 0, that is, it does not meet the basic job requirements and will not be included in the personnel allocation decision for this job. Q is the penalty coefficient, is the weight of the ability factor.

[0047] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A human resource allocation system for construction enterprise project groups based on multi-objective optimization, characterized in that Including: A model construction module, which is used to construct a multi-objective optimization model including maximizing the overall person-job matching degree of the project group, optimizing the age structure of the team members, and minimizing the human resource cost, and set the allocation constraints for employees and positions; An information acquisition module, which is signal-connected to the model construction module, and is used to acquire employee information and position information, and transmit the acquired information to the model construction module and the matching degree quantification module; A matching degree quantification module, which is signal-connected to the information acquisition module and the model construction module, and is used to receive the employee information and position information transmitted by the information acquisition module, quantify the person-job matching degree based on the position competency model and the personnel portrait, and evaluate the rationality of the age structure of the team members by using the employee marginal contribution rate curve, and transmit the quantification result signal to the model construction module and the solution generation module; A solution generation module, which is signal-connected to the model construction module and the matching degree quantification module, and is used to receive the multi-objective optimization model transmitted by the model construction module and the quantification result signal transmitted by the matching degree quantification module, solve the multi-objective optimization model by using an improved NSGA-II algorithm, and obtain and output a human resource allocation solution.

2. The human resource allocation system for construction enterprise project groups based on multi-objective optimization according to claim 1, characterized in that: The employee information includes the employee's skill level, work experience, educational background, performance, professional qualification certificate, and age information; the position information includes the duty requirements, skill requirements, experience requirements, educational requirements, qualification certificate requirements, and age structure requirements of the position.

3. The human resource allocation system for construction enterprise project groups based on multi-objective optimization according to claim 2, characterized in that, The matching degree quantification module includes: A competency model construction unit, which is used to construct a competency model for each position according to the position information and determine the weights of each competency index; A personnel portrait construction unit, which is used to construct a personnel portrait of the employee according to the employee information and quantify the scores of each competency index; A matching degree calculation unit, which is used to calculate the person-job matching degree score of each employee and each position based on the competency model of the position and the personnel portrait of the employee.

4. The human resource allocation system for construction enterprise project groups based on multi-objective optimization according to claim 2, wherein, The matching degree quantification module further includes an age structure evaluation unit, which includes: A contribution rate curve fitting subunit, which is used to fit the employee marginal contribution rate curve based on the historical performance data and age information of the employee; A contribution level determination subunit, which is used to determine the expected contribution level of employees in different age groups according to the employee marginal contribution rate curve; A team contribution calculation subunit, which is used to calculate the overall expected contribution of the team based on the age distribution of the current team members and the expected contribution levels of employees in each age group; A structure rationality evaluation subunit, which is used to compare the overall expected contribution of the team with the expected contribution under the preset reasonable age structure, and evaluate the rationality of the current team age structure.

5. The human resource allocation system for construction enterprise project groups based on multi-objective optimization according to claim 1, characterized in that The method for the solution generation module to solve the multi-objective optimization model by using an improved NSGA-II algorithm, obtain and output a human resource allocation solution includes: S101. Perform double-layer segmented coding on the chromosome, where the chromosome is used to represent both the person-project allocation information and the person-position allocation information; among them, the first-layer chromosome represents the project to which the person is assigned, and the second-layer chromosome represents the matching degree, expected salary, and age of the person and the position. S102. Use non - dominated sorting based on an early rejection strategy to accelerate the sorting process of population individuals; S103. Conduct individual selection based on an improved niche strategy, where the niche radius is dynamically determined according to the Euclidean distance between population individuals; S104. Use a partially - mapped crossover operator for crossover operations to ensure the uniqueness of genes in the chromosomes after crossover; perform single - point mutation operations on the chromosomes and perform duplicate - removal processing to ensure the uniqueness of genes in the mutated chromosomes; S105. Terminate the algorithm according to the number of iterations and fitness values, and output the Pareto - optimal solution set as the human resource allocation plan.

6. The human resource allocation system for construction enterprise project groups based on multi-objective optimization according to claim 1, characterized in that The allocation constraints for employees and positions set by the model construction module include: Each employee can be assigned to at most one position, and at the same time, it is allowed that some employees are not assigned; Each position must be assigned one employee; Set priority weight coefficients for each project, where the priority weight coefficients are values between 0 and 1, and the sum of the priority weight coefficients of all projects is 1.

7. The human resource allocation system for construction enterprise project groups based on multi-objective optimization according to claim 1, wherein The objective function of the multi - objective optimization model constructed by the model construction module includes: S201. Maximize the overall person-position matching degree of the project portfolio , expressed as: ； Among them, represents the function of maximizing the overall person-position matching degree of the project portfolio of the project portfolio, represents the priority weight coefficient of project h, N is the total number of projects, n is the personnel number, and m is the position number; represents the position matching degree between position j of project h and person i; is a 0-1 variable. When the value is 1, it means that person i has been arranged to hold position j. S202. Optimize the age structure of the team members , expressed as: ； Among them, represents the function of maximizing the age structure of the team members ; represents the evaluation value of the rationality of the age structure of the team members for project h; S203. Minimize human resource costs , expressed as: ； Among them, represents the function of minimizing human resource costs , represents the expected salary of person i for position j.

8. The human resource allocation system for construction enterprise project groups based on multi-objective optimization according to claim 5, wherein The method for conducting individual selection based on the improved niche strategy includes: S301. Calculate the Euclidean distance between individuals in the population: ； Among them, x and y represent two random individuals in the population, represents the Euclidean distance between x and y, and xᵢ and yᵢ are the values of the i-th objective function corresponding to individual x and individual y, respectively; S302. After calculating the Euclidean distance between each individual and other individuals, take the average value of the minimum Euclidean distance values of all individuals as the initial value of the niche radius; S303. Dynamically adjust the niche radius through dynamic iteration, and the niche radius gradually decreases according to the following formula: ; represents the current niche radius, is a constant; gs is the current iteration number, gs max is the maximum number of iterations; S304. When the Euclidean distance between two individuals x and y is less than the current niche radius compare the fitness values of these two individuals, and penalize the individual with the lower fitness value to reduce its probability of being selected.

9. The human resource allocation system for construction enterprise project groups based on multi-objective optimization according to claim 7, wherein The calculation process of the position matching degree includes the following sub - steps: S401. Analyze the position attributes, judge the ability and quality required for the position, denote the set of positions that need personnel in the project as J, and the set of available personnel for each position as I; S402. Obtain the matching results of person i and position j on the t-th qualification factor respectively , the matching results of person i and position j on the s-th ability factor , and the competency evaluation value of person i in position j ; S403. Based on the above evaluation results, calculate the job matching degree of person i on job j : ； Among them, is a piecewise function and ; Q is the penalty coefficient, is the weight of the ability factor.

Images