A method and system for optimizing the allocation of human resources

Abstract

The present invention discloses a method and system for optimizing the allocation of human resources, which relates to the technical field of human resources. By extracting the historical record information and current situation information of each employee from the human resources information system, a multi-faceted set of employee historical data and a set of current situation information are constructed. Through data preprocessing and feature extraction, managers can accurately evaluate the comprehensive ability coefficient Zhxs and task complexity coefficient Rfxs of each employee, thus realizing the scientific and reasonable allocation of tasks. Using a resource allocation analysis model constructed by a convolutional neural network, combined with the comprehensive ability coefficient Zhxs and the task complexity coefficient Rfxs, the saturation evaluation index Bpzs of employees is accurately fitted and obtained. This intelligent evaluation method greatly improves the accuracy of task allocation and further avoids the uncertainty brought by relying on experience and subjective judgment in traditional methods.

Description

Technical Field

[0001] The present invention relates to the technical field of human resources, and specifically to a method and system for optimizing the allocation of human resources. Background Art

[0002] In the field of human resource management, the optimization allocation method is the key to ensuring the efficient operation of organizational resources. Specifically for the task scheduling problem in human resource management, it is particularly important to reasonably allocate tasks to make full use of employees' capabilities, avoid overwork and resource waste. Especially in the aspect of employee task scheduling, it is necessary to comprehensively analyze whether the human resources are in a balanced state based on the comprehensive capabilities of each employee and the current unprocessed tasks, so as to improve work efficiency and employee satisfaction.

[0003] In the process of task scheduling, existing methods often face many challenges and deficiencies. Traditional manual scheduling methods rely on the subjective experience and intuition of managers, making it difficult to achieve precise balance and optimization, thus easily leading to unbalanced resource allocation and low efficiency. Some existing rule-based automated methods can improve efficiency to a certain extent, but they often lack a comprehensive analysis of employees' historical data and current situation, and it is difficult to accurately evaluate employees' true workload and capabilities. In addition, many existing methods lack a comprehensive analysis of employees' historical data and current situation information, and cannot accurately evaluate employees' comprehensive capabilities and task complexity. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a method and system for optimizing the allocation of human resources, which solves the problems in the above background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A method for optimizing the allocation of human resources includes the following steps.

[0006] S1. Extract relevant historical record information of each employee from the human resource information system in advance to construct an employee historical data set, and at the same time track and record the relevant current situation information set of each employee. According to the relevant current situation information set of each employee, extract the relevant complex information of the corresponding assigned tasks.

[0007] S2. Perform data preprocessing on the employee historical data set and the relevant current situation information set of each employee obtained in step S1, including data cleaning and data standardization processing.

[0008] S3. Extract features from the preprocessed historical employee data set and the relevant current situation information of each employee to obtain the task completion quantity Rwc, the error quantity Cwz, the number of collaborative workers Xzrw for the tasks to be processed, and the reserved duration Ysc of the tasks to be processed respectively. By correlating the task completion quantity Rwc with the error quantity Cwz, obtain the comprehensive ability coefficient Zhxs of each employee, and by correlating the number of collaborative workers Xzrw for the tasks to be processed with the reserved duration Ysc of the tasks to be processed, obtain the current task complexity coefficient Rfxs of each employee. Use a convolutional neural network to construct a trained resource allocation analysis model, and then combine the comprehensive ability coefficient Zhxs with the task complexity coefficient Rfxs of the corresponding employee to fit and obtain the saturation evaluation index Bpzs of the corresponding employee;

[0009] S4. Preset a balance threshold K. By comparing the saturation evaluation index Bpzs of each employee, obtain the imbalance rate Shs. By comparing and analyzing the imbalance rate Shs with the balance threshold K, comprehensively judge whether the current human resources are in a balanced state in terms of task scheduling. If not, send out a configuration optimization instruction and take corresponding optimization measures.

[0010] Preferably, S1 specifically includes the following steps:

[0011] S11. The relevant historical record information includes the task completion quantity Rwc and the error quantity Cwz of each employee's tasks in each monitoring period;

[0012] S12. The relevant current situation information set includes the relevant data information to be processed of each employee and the relevant complex information of the corresponding assigned tasks. Among them, the relevant data information to be processed of each employee includes the current number of urgent tasks Jjrz, the reserved duration Ysc of the tasks to be processed, and the number of collaborative workers Xzrw for the tasks to be processed;

[0013] The relevant complex information of the corresponding assigned tasks includes the current task quantity Drz to be processed by each employee. By combining the task completion quantity Rwc of each employee's tasks in each monitoring period and using the statistical algorithm of finding the mean value, obtain the mean value of the task processing quantity of each employee within the monitoring period 。

[0014] Preferably, S2 specifically includes the following steps:

[0015] S21. Detect and delete the repeatedly collected data information to avoid bias in analysis caused by data repetition, and identify missing data to detect and repair outliers;

[0016] S22. Use dimensionless processing technology to standardize the data processed in step S21, eliminating the unit and dimension differences in the data.

[0017] Preferably, S3 specifically includes the following steps:

[0018] S31. Use a convolutional neural network to initially construct an original model, and train and test the original model with the employee historical data set and the relevant current situation information set. Then, use the trained original model as a resource recognition model, respectively obtain the feature information in the resource recognition model, and use the obtained feature information to train and test the resource recognition model. Finally, use the trained resource recognition model as a resource allocation analysis model.

[0019] Preferably, S3 further includes:

[0020] S32. According to the employee historical data set, by correlating the task completion quantity Rwc and the error quantity Cwz, and after linear normalization processing, calculate the comprehensive ability coefficient Zhxs of each employee. Specifically, obtain it according to the following formula:

[0021] In the formula, n represents the number of monitoring time periods, i = 1, 2, 3,..., n, represents the task completion quantity in the i-th time period, represents the average value of the task completion quantity within the monitoring period, represents the error quantity in the i-th time period, represents the average value of the error quantity within the monitoring period, and are both weight coefficients, where 0 < ≤1, 0 < ≤1, and =1.

[0022] Preferably, S3 further includes:

[0023] S33. According to the relevant current situation information set, by correlating the number of collaborative workers Xzrw of the task to be processed and the remaining duration Ysc of the task to be processed, and after linear normalization processing, obtain the task complexity coefficient Rfxs of each employee currently. Specifically, obtain it according to the following formula:

[0024] In the formula, represents the number of urgent tasks, , and respectively represent the number of collaborative workers Xzrw of the task to be processed, the remaining duration Ysc of the task to be processed, and the number of urgent tasks are the weight coefficients of ≤ 1, 0 < ≤ 1, 0 < ≤ 1, and a1 + a2 + a3 = 1, where V represents a corrected constant.

[0025] Preferably, S3 further includes:

[0026] S34. By transmitting the task complexity coefficient Rfxs and the comprehensive ability coefficient Zhxs of the corresponding employee to the resource allocation analysis model and performing linear normalization processing, the saturation evaluation index Bpzs of the corresponding employee is obtained. Specifically, it is obtained according to the following formula:

[0027] In the formula, represents the current workload of the j-th employee to be processed, represents the task complexity coefficient Rfxs of the j-th employee, represents the comprehensive ability coefficient of the j-th employee, represents the average value of the task processing volume of the j-th employee during the monitoring period.

[0028] Preferably, S4 specifically includes the following steps:

[0029] S41. By using the saturation evaluation index Bpzs of the corresponding employee obtained in step S34 and according to the algorithm for calculating the mean value in statistics, calculate the mean value of the saturation evaluation index of all employees ;

[0030] S42. According to the mean value of the saturation evaluation index of all employees, and compare its size with the saturation evaluation index Bpzs of each employee to determine the tolerance of each employee to the current task situation. Specifically, it includes the following content:

[0031] If the saturation evaluation index Bpzs exceeds the mean value of the saturation evaluation index of all employees, at this time, it is determined that the tolerance of the corresponding employee to the current task situation is in an abnormal state. At this time, the number of employees in the abnormal state Yss will be counted and corresponding records will be made;

[0032] If the saturation evaluation index Bpzs does not exceed the mean value of the saturation evaluation index of all employees, at this time, it is determined that the tolerance of the corresponding employee to the current task situation is not in an abnormal state;

[0033] S43. Calculate the imbalance rate Shs.

[0034] Preferably, S4 further includes:

[0035] S44. Preset a balance threshold K. By comparing and analyzing the balance threshold K with the imbalance rate Shs, comprehensively judge whether the current human resources are in a balanced state in task scheduling, which specifically includes the following content:

[0036] If the imbalance rate Shs ≥ the balance threshold K, it will be comprehensively judged that the current human resources are not in a balanced state in task scheduling, and a configuration optimization instruction will be sent outwards. Transfer the tasks to be completed from the employees in the abnormal state to the employees not in the abnormal state, and regularly hold meetings to understand the work status and needs of each employee, and adjust the task allocation in a timely manner;

[0037] If the imbalance rate Shs < the balance threshold K, it will be comprehensively judged that the current human resources are in a balanced state in task scheduling. At this time, no configuration optimization instruction will be sent outwards, and on the premise of ensuring task balance, maintain the existing task allocation and work arrangement, and regularly check and evaluate the task allocation situation.

[0038] A human resource optimization configuration system includes a data collection module, a data preprocessing module, a resource analysis module, and a configuration management module;

[0039] The data collection module extracts the relevant historical record information of each employee from the human resource information system in advance, constructs a set of employee historical data, and simultaneously tracks and records the relevant current situation information set of each employee. According to the relevant current situation information set of each employee, extract the relevant complex information of the corresponding assigned tasks;

[0040] The data preprocessing module performs data preprocessing on the obtained set of employee historical data and the relevant current situation information set of each employee, including data cleaning and data standardization processing;

[0041] The resource analysis module extracts features from the preprocessed set of employee historical data and the relevant current situation information set of each employee to respectively obtain the task completion quantity Rwc, the error quantity Cwz, the number of collaborative workers Xzrw for the tasks to be processed, and the reserved duration Ysc for the tasks to be processed. By associating the task completion quantity Rwc with the error quantity Cwz, obtain the comprehensive ability coefficient Zhxs of each employee, and by associating the number of collaborative workers Xzrw for the tasks to be processed with the reserved duration Ysc for the tasks to be processed, obtain the current task complexity coefficient Rfxs of each employee. Use a convolutional neural network to construct a trained resource configuration analysis model, and then combine the comprehensive ability coefficient Zhxs with the task complexity coefficient Rfxs of the corresponding employee to fit and obtain the saturation evaluation index Bpzs of the corresponding employee;

[0042] The configuration management module pre-sets a balance threshold K, compares the saturation evaluation indices Bpzs of each employee to obtain an imbalance rate Shs, and compares and analyzes the imbalance rate Shs with the balance threshold K to comprehensively determine whether the current human resources are in a balanced state in terms of task scheduling. If not, it issues a configuration optimization instruction externally and takes corresponding optimization measures.

[0043] The present invention provides a method and system for optimizing the allocation of human resources, having the following beneficial effects:

[0044] (1) By extracting the historical records and current status information of each employee from the human resource information system, a multi-faceted set of employee historical data and a set of current status information are constructed. Through data preprocessing and feature extraction, managers can accurately evaluate the comprehensive ability coefficient Zhxs and task complexity coefficient Rfxs of each employee, thus realizing the scientific and reasonable allocation of tasks. Using a resource allocation analysis model constructed by a convolutional neural network, combined with the comprehensive ability coefficient Zhxs and the task complexity coefficient Rfxs, the saturation evaluation index Bpzs of employees is accurately fitted. This intelligent evaluation method greatly improves the accuracy of task allocation and further avoids the uncertainties brought by relying on experience and subjective judgment in traditional methods. By setting a balance threshold K, the saturation evaluation indices Bpzs of each employee are compared to calculate the imbalance rate Shs. Then, by comparing and analyzing the imbalance rate Shs with the balance threshold K, it is comprehensively determined whether the current human resources are in a balanced state in terms of task scheduling. If not, the system will automatically issue a configuration optimization instruction and take corresponding optimization measures. This mechanism further ensures the balanced use of human resources, reduces resource waste and the problem of employees working overtime. Through data cleaning and standardization processing, the accuracy and consistency of the data are guaranteed. The application of feature extraction and convolutional neural network makes the analysis results more reliable and persuasive, provides a scientific basis for management decisions, and reduces the blindness and randomness in human resource management. By reasonably allocating tasks and timely adjusting resource allocation, not only the overall work efficiency is improved, but also the workload of employees is reduced, and the job satisfaction of employees is improved. The work enthusiasm of employees and the overall performance of the organization have been significantly improved. In short, through the comprehensive analysis of employees' historical data and current data, combined with advanced convolutional neural network technology, the method further realizes the intelligence and scientification of human resource optimization allocation, providing strong technical support for enterprises to improve management level and competitiveness.

[0045] The original model is initially constructed using a convolutional neural network, and the original model is trained and tested with the employee historical data set and the relevant current situation information set to ensure the initial accuracy and stability of the model. The trained original model is used as a resource recognition model to further obtain feature information, and the resource recognition model is retrained and tested. The finally trained resource recognition model is used as a resource allocation analysis model. This process makes full use of the advantages of convolutional neural networks in processing complex data and identifying patterns, ensuring the efficiency and accuracy of the model. This calculation method of the comprehensive ability coefficient Bpzs based on historical data can comprehensively and accurately reflect the actual work ability of employees, ensuring the scientificity and rationality of task allocation. Using the calculation formula of the comprehensive ability coefficient, the comprehensive ability of employees can be accurately evaluated, thus realizing the precise optimization of employee task allocation. This not only improves the rationality and efficiency of task allocation, but also enables scientific task scheduling according to the actual abilities of employees, further reducing the subjective judgment and experience dependence problems in traditional methods, making the task allocation more reasonable.

[0046] (3) Use the imbalance rate formula to evaluate the balance of task scheduling, which reduces the blindness and randomness in human resource management to promptly detect situations of unbalanced human resource allocation. When the imbalance rate exceeds the set balance threshold, the system can automatically issue a configuration optimization instruction to adjust task allocation, ensuring work efficiency and employee health. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the steps of a human resource optimization and allocation method of the present invention;

[0048] Figure 2 It is a schematic diagram of the process of a human resource optimization and allocation system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. Embodiment 1

[0050] Please refer to Figure 1 , the present invention provides a human resource optimization and allocation method, including the following steps,

[0051] S1. Extract the relevant historical record information of each employee from the human resource information system in advance to construct an employee historical data set. At the same time, track and record the relevant current status information set of each employee, and extract the relevant complex information of the corresponding assigned tasks according to the relevant current status information set of each employee;

[0052] S2. Perform data preprocessing on the employee historical data set and the relevant current status information set of each employee obtained in step S1, including data cleaning and data standardization processing;

[0053] S3. Extract features from the preprocessed employee historical data set and the relevant current status information set of each employee to respectively obtain the task completion quantity Rwc, the error quantity Cwz, the number of collaborative workers Xzrw for the tasks to be processed, and the reserved duration Ysc of the tasks to be processed. By associating the task completion quantity Rwc with the error quantity Cwz, obtain the comprehensive ability coefficient Zhxs of each employee, and by associating the number of collaborative workers Xzrw for the tasks to be processed with the reserved duration Ysc of the tasks to be processed, obtain the current task complexity coefficient Rfxs of each employee. Use a convolutional neural network to construct a trained resource allocation analysis model, and then combine the comprehensive ability coefficient Zhxs with the task complexity coefficient Rfxs of the corresponding employee to fit and obtain the saturation evaluation index Bpzs of the corresponding employee;

[0054] S4. Preset a balance threshold K, compare the saturation evaluation index Bpzs of each employee to obtain the imbalance rate Shs, and compare and analyze the imbalance rate Shs with the balance threshold K to comprehensively judge whether the current human resources are in a balanced state in terms of task scheduling. If not, send out a configuration optimization instruction and take corresponding optimization measures.

[0055] In this embodiment, relevant historical record information and current situation information of each employee are extracted from the human resources information system in advance through step S1, and an employee historical data set and a current situation information set are constructed, enabling the method to comprehensively grasp the work history and current work status of employees. This step can effectively extract complex information for task allocation, laying a solid foundation for subsequent analysis. Secondly, in step S2, data preprocessing is performed on the obtained employee historical data and current situation information, including data cleaning and data standardization processing, ensuring the accuracy and consistency of the data. The data preprocessing step can significantly improve the accuracy and reliability of subsequent analysis. In step S3, through feature extraction, the comprehensive ability coefficient Zhxs of each employee is obtained; at the same time, through the current task complexity coefficient Rfxs of each employee, this multi-dimensional feature extraction method can comprehensively and accurately evaluate the ability of employees and the complexity of tasks. In addition, a resource allocation analysis model constructed using a convolutional neural network fits the saturation evaluation index Bpzs of employees, further improving the scientific nature and accuracy of the evaluation. In step S4, by presetting a balance threshold K and comparing the saturation evaluation index Bpzs of each employee, the imbalance rate Shs is obtained. By comparing and analyzing the imbalance rate Shs with the balance threshold K, it is possible to comprehensively judge whether the current human resources are in a balanced state in terms of task scheduling. If not in a balanced state, a configuration optimization instruction will be issued and corresponding optimization measures will be taken. This step can not only timely detect and correct the imbalance problem of task allocation, but also improve the rationality and efficiency of task allocation through reasonable optimization measures. In short, through scientific analysis and evaluation, this method can achieve intelligent and precise management of employee task allocation, further avoiding the problems of unbalanced resource allocation and low efficiency caused by subjective judgment in traditional methods. It not only improves the work efficiency and satisfaction of employees, but also effectively optimizes the human resources configuration of the enterprise, with significant beneficial effects. Embodiment 2

[0056] Please refer to Figure 1 , specifically: S1 specifically includes the following steps:

[0057] S11. The relevant historical record information includes the task completion quantity Rwc and the error quantity Cwz of each employee's tasks in each monitoring period.

[0058] S12. The relevant current situation information set includes the relevant data information to be processed of each employee and the relevant complex information of the corresponding assigned tasks. Among them, the relevant data information to be processed of each employee includes the current number of urgent tasks Jjrz, the reserved duration Ysc of the tasks to be processed, and the number of collaborative workers Xzrw of the tasks to be processed.

[0059] The relevant complex information of the corresponding assigned tasks includes the current task volume Drz to be processed by each employee, and combines the task completion volume Rwc of each employee's tasks in each monitoring period. Through the statistical algorithm of calculating the mean value, the mean value of the task processing volume of each employee within the monitoring period is obtained. 。

[0060] S2 specifically includes the following steps:

[0061] S21. Detect and delete the repeatedly collected data information to avoid bias in analysis caused by data repetition, and identify missing data to detect and repair outliers;

[0062] S22. Use the dimensionless processing technology to standardize the data processed in step S21, and eliminate the unit and dimension differences in the data.

[0063] In this embodiment, first, in step S1, by collecting and recording the relevant historical record information and current situation information sets of each employee, the work history and current work status of the employees are grasped from multiple dimensions. The historical record information provides accurate basic data for subsequent analysis. In step S12, the current situation information set includes the number of urgent tasks Jjrz of each employee, the reserved duration Ysc of the tasks to be processed, the number of collaborative workers Xzrw of the tasks to be processed, and the current task volume Drz to be processed by each employee. By combining the task completion volume Rwc of each employee within the monitoring period and using the statistical algorithm of calculating the mean value, the mean value of the task processing volume of the employees within the monitoring period is obtained. This process ensures the accurate assessment of the current task load of the employees and provides a scientific basis for task allocation. Secondly, in step S21, by detecting and deleting the repeatedly collected data information, the bias caused by data repetition in analysis is further avoided. At the same time, by identifying and repairing missing data, detecting and repairing outliers, the integrity and accuracy of the data are further guaranteed. This process greatly improves the data quality and provides a reliable data basis for subsequent analysis and processing. In step S22, by performing dimensionless processing on the data, the unit and dimension differences in the data are eliminated, and the standardization processing of the data is realized. This step enables effective comparison and analysis of data with different units and scales, and improves the comparability and processing efficiency of the data. In short, through comprehensive collection and processing of the historical records and current situation information of employees, combined with scientific statistics and data processing technologies, this method not only improves the quality and accuracy of the data, but also provides strong support for the intelligence and scientific nature of task allocation. Through these steps, the comprehensive capabilities and task complexities of employees can be accurately evaluated, so as to realize the optimal allocation of human resources, avoid problems such as unbalanced resource allocation and low efficiency, and have significant beneficial effects. Embodiment 3

[0064] Please refer toFigure 1 , specifically: S3 specifically includes the following steps:

[0065] S31. Initially construct an original model using a convolutional neural network, train and test the original model with the employee historical data set and the relevant current situation information set, and use the trained original model as a resource recognition model. Respectively obtain the feature information in the resource recognition model, and use the obtained feature information to train and test the resource recognition model, and use the trained resource recognition model as a resource allocation analysis model.

[0066] S3 also includes:

[0067] S32. According to the employee historical data set, by correlating the task completion quantity Rwc and the error quantity Cwz, and after linear normalization processing, calculate and obtain the comprehensive ability coefficient Zhxs of each employee, specifically obtained according to the following formula:

[0068] ; where n represents the number of monitoring periods, i = 1, 2, 3,..., n, represents the task completion quantity in the i-th period, represents the average value of the task completion quantity within the monitoring period, represents the error quantity in the i-th period, represents the average value of the error quantity within the monitoring period, and are both weight coefficients, where 0 < ≤ 1, 0 < ≤ 1, and = 1.

[0069] The above-mentioned task completion quantity Rwc and error quantity Cwz can both be collected and obtained through the human resource information system;

[0070] In this embodiment, the method comprehensively analyzes and processes the historical data and current situation information of employees by using a convolutional neural network and a scientific calculation method, so as to achieve accurate evaluation and optimization of employee task allocation, and has significant beneficial effects. First, in step S31, an original model is initially constructed by using a convolutional neural network, and the original model is trained and tested with the historical data set of employees and the relevant current situation information set to ensure that the model can accurately identify and extract key feature information; the trained original model is used as a resource identification model to further obtain and extract feature information, and the resource identification model is retrained and tested, and finally a resource allocation analysis model is formed. This process continuously optimizes the model to ensure that the resource allocation analysis model has high accuracy and high reliability, and can accurately identify and evaluate the capabilities of employees and the task complexity. By calculating the comprehensive ability coefficient Zhxs of each employee, the task completion situation and error rate of employees in different monitoring periods can be comprehensively considered, and the comprehensive ability of employees can be evaluated comprehensively and accurately. The linear normalization process ensures the standardization of the data, making the calculation of the comprehensive ability coefficient more accurate and reasonable. In short, through the convolutional neural network and scientific calculation methods, this method can comprehensively and accurately identify and evaluate the capabilities of employees and the task complexity. By continuously optimizing the model and accurately calculating the data, the rationality and efficiency of task allocation are ensured, thereby improving the scientific nature and effectiveness of human resource management, and having significant beneficial effects. Embodiment 4

[0071] Please refer to Figure 1 , specifically: S3 further includes:

[0072] S33. According to the relevant current situation information set, by correlating the number of collaborative workers Xzrw of the task to be processed with the remaining duration Ysc of the task to be processed, and after linear normalization processing, the current task complexity coefficient Rfxs of each employee is obtained. Specifically, it is obtained according to the following formula:

[0073] ; in the formula, represents the number of urgent tasks, , and respectively represent the number of collaborative workers Xzrw of the task to be processed, the remaining duration Ysc of the task to be processed, and the number of urgent tasks 's weight coefficients, where 0 < ≤ 1, 0 < ≤ 1, 0 < ≤ 1, and a1 + a2 + a3 = 1, V represents a correction constant.

[0074] The above-mentioned number of collaborative workers Xzrw of the task to be processed, the remaining duration Ysc of the task to be processed, and the number of urgent tasks All can be collected and obtained through the human resources information system;

[0075] In this embodiment, first, through step S33, according to the relevant current situation information set, the current task complexity coefficient Rfxs of each employee is obtained. This method can comprehensively consider the complexity of the tasks currently faced by employees, further ensuring the rationality and scientific nature of task allocation. Through this calculation method, the current task complexity of each employee can be accurately evaluated, so as to better allocate tasks and configure resources. Specifically, the beneficial effects of this method are as follows: By considering multiple factors, it reflects the complexity of employees' current tasks in multiple dimensions, further avoiding the one-sidedness of single-dimensional evaluation. Through linear normalization processing, the dimensional differences between different data are eliminated, making each factor comparable in calculation and improving the accuracy of the evaluation results. By setting different weight coefficients, the influence degree of each factor can be flexibly adjusted according to actual needs, making the model have higher adaptability and flexibility. Using a data-driven method, it avoids the problems of subjective judgment and experience dependence in traditional methods, making task allocation and resource configuration more scientific and reasonable. By calculating the task complexity coefficient Rfxs, tasks can be better allocated, avoiding resource waste and overloading of employees, and further improving the overall work efficiency and employee satisfaction. In short, through scientific data processing and optimization techniques, this method comprehensively evaluates the task complexity coefficient of employees, can achieve more accurate task allocation and resource configuration, which not only improves the rationality and efficiency of task allocation, but also can perform scientific task scheduling according to the actual capabilities and task complexity of employees, with significant beneficial effects. Embodiment 5

[0076] Please refer to Figure 1 , specifically: S3 further includes:

[0077] S34. By transmitting the task complexity coefficient Rfxs and the comprehensive ability coefficient Zhxs of the corresponding employee to the resource allocation analysis model, and after linear normalization processing, the saturation evaluation index Bpzs of the corresponding employee is obtained, which is specifically obtained according to the following formula:

[0078] ; where represents the current workload to be processed of the j-th employee, represents the task complexity coefficient Rfxs of the j-th employee, represents the comprehensive ability coefficient of the j-th employee, represents the average value of the task processing volume of the j-th employee during the monitoring period.

[0079] In this embodiment, by inputting the task complexity coefficient and the comprehensive employee ability coefficient into the resource allocation analysis model and combining linear normalization processing, the saturation evaluation index Bpzs of each employee can be calculated more accurately. This index reflects the work saturation degree of employees under the current task load. Using the mean value of the task processing volume within the monitoring period as a reference can more objectively evaluate the task processing ability of employees. The saturation evaluation index Bpzs calculated through the formula provides a basis for managers to help them make reasonable resource allocation and task scheduling decisions. By analyzing the task complexity and comprehensive ability of each employee, tasks can be allocated more effectively to ensure that each employee works within their tolerance range, thereby improving the overall work efficiency and quality. Through continuous monitoring and analysis of the employee saturation evaluation index Bpzs, it can help managers better conduct performance management and personalized development planning to improve employee job satisfaction and performance. These data and calculation processes not only help optimize the existing work process but also support long-term human resource planning and management decisions, contributing to the organization achieving higher operational efficiency and employee satisfaction. Example 6

[0080] Please refer to Figure 1 , specifically: S4 specifically includes the following steps:

[0081] S41. Obtain the saturation evaluation index Bpzs of the corresponding employees in step S34, and calculate the mean value of the overall employee saturation evaluation index according to the algorithm for calculating the mean value in statistics. ;

[0082] S42. According to the mean value of the overall employee saturation evaluation index , compare its size with the saturation evaluation index Bpzs of each employee to determine the tolerance degree of each employee to the current task situation, which specifically includes the following content:

[0083] If the saturation evaluation index Bpzs exceeds the mean value of the overall employee saturation evaluation index , at this time, it will be determined that the tolerance degree of the corresponding employee to the current task situation is in an abnormal state. At this time, the number of employees in the abnormal state Yss will be counted and corresponding records will be made;

[0084] If the saturation evaluation index Bpzs does not exceed the mean value of the overall employee saturation evaluation index , at this time, it will be determined that the tolerance degree of the corresponding employee to the current task situation is not in an abnormal state;

[0085] S43. Calculate the imbalance rate Shs.

[0086] S4 also includes:

[0087] S44, presetting a balance threshold K, and comparing and analyzing the balance threshold K with the imbalance rate Shs to comprehensively determine whether the current human resources are in a balanced state in terms of task scheduling, specifically including the following contents:

[0088] If the imbalance rate Shs ≥ the balance threshold K, it will be comprehensively judged that the current human resources are not in a balanced state in terms of task scheduling, and a configuration optimization instruction will be issued to transfer the tasks to be completed from employees in abnormal states to employees who are not in abnormal states. If some tasks are urgent and the workload is large, you can consider temporarily adding manpower or outsourcing to complete some tasks, reasonably arrange overtime and rest time to ensure that employees have enough rest time to restore their energy, consider flexible working hours or remote work to reduce the burden on employees, and hold meetings regularly to understand the work status and needs of each employee and adjust task allocation in a timely manner;

[0089] If the imbalance rate Shs is less than the balance threshold K, it will be comprehensively judged that the current human resources are in a balanced state in terms of task scheduling. At this time, no configuration optimization instructions will be issued to the outside. On the premise of ensuring task balance, the existing task allocation and work arrangements will be maintained. At the same time, the task allocation situation will be regularly checked and evaluated to ensure that it continues to be balanced. Regular training will be organized to help employees improve their skills and knowledge and adapt to future work challenges.

[0090] In this embodiment, by regularly evaluating the saturation evaluation index Bpzs of employees, managers can understand the current work tolerance of employees. When employees have a moderate workload, they are more likely to maintain high efficiency and satisfaction, thereby improving work performance and productivity. By comparing the saturation evaluation index Bpzs of individual employees with the overall mean, employees in abnormal states can be found in time. For these employees, measures such as task reallocation, additional manpower or adjustment of work arrangements can be taken to reduce their work pressure and prevent long-term fatigue accumulation. Using the imbalance rate Shs to evaluate the balance of task scheduling can help decision makers quickly identify imbalances. When the imbalance rate Shs is higher than the set balance threshold, the resource allocation strategy can be adjusted in time to ensure that the task can be completed on time while ensuring the balance of employees' workload. Through regular task allocation evaluation and employee demand surveys, organizations can be helped to adapt to changing work environments and needs. Regular training and skill improvement activities can also enhance employees' adaptability and help them cope with future work challenges, thereby promoting the long-term sustainable development of the organization. In short, this method helps to improve employees' work efficiency and satisfaction, reduce employees' work pressure, and optimize the organization's task scheduling and resource allocation, laying the foundation for the sustainable development of the organization. Example 7

[0091] Please refer to Figure 1and Figure 2 , specifically: a human resource optimization and allocation system, including a data collection module, a data preprocessing module, a resource analysis module, and a configuration management module;

[0092] The data collection module extracts the relevant historical record information of each employee from the human resource information system in advance, constructs a set of employee historical data, and at the same time tracks and records the relevant current situation information set of each employee, and extracts the relevant complex information of the corresponding assigned tasks according to the relevant current situation information set of each employee;

[0093] The data preprocessing module performs data preprocessing on the obtained set of employee historical data and the relevant current situation information set of each employee, including data cleaning and data standardization processing;

[0094] The resource analysis module extracts features from the preprocessed set of employee historical data and the relevant current situation information set of each employee to respectively obtain the task completion quantity Rwc, the error quantity Cwz, the number of collaborative workers Xzrw for the tasks to be processed, and the reserved duration Ysc of the tasks to be processed. By associating the task completion quantity Rwc with the error quantity Cwz, the comprehensive ability coefficient Zhxs of each employee is obtained, and by associating the number of collaborative workers Xzrw for the tasks to be processed with the reserved duration Ysc of the tasks to be processed, the current task complexity coefficient Rfxs of each employee is obtained. Using a convolutional neural network, a trained resource allocation analysis model is constructed, and then by combining the comprehensive ability coefficient Zhxs with the task complexity coefficient Rfxs of the corresponding employee, the saturation evaluation index Bpzs of the corresponding employee is obtained by fitting;

[0095] The configuration management module pre-sets a balance threshold K, compares the saturation evaluation index Bpzs of each employee to obtain the imbalance rate Shs, and compares and analyzes the imbalance rate Shs with the balance threshold K to comprehensively judge whether the current human resources are in a balanced state in terms of task scheduling. If not in a balanced state, a configuration optimization instruction is sent outwards and corresponding optimization measures are taken.

[0096] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for optimizing human resources allocation, characterized in that: The following steps are included: S1. Extract relevant historical record information of each employee from the human resources information system in advance, build an employee historical data set, and track and record relevant current information sets of each employee. According to the relevant current information sets of each employee, extract relevant complex information of the corresponding assigned tasks; S1 specifically includes the following steps: S11, the relevant historical record information includes the task completion amount Rwc and error amount Cwz of each employee's task in each monitoring period; S12, the relevant status information set includes relevant pending data information of each employee and relevant complex information of the corresponding assigned tasks, wherein the relevant pending data information of each employee includes the current number of expedited tasks of each employee Jjrz, the reserved time of the pending tasks Ysc and the number of collaborative workers Xzrw of the pending tasks; The complex information related to the corresponding assigned tasks includes the current amount of tasks to be processed by each employee Drz, and combined with the task completion amount Rwc of each employee in each monitoring period, the average of the task processing amount of each employee in the monitoring period is obtained through the statistical mean algorithm ; S2, preprocessing the employee historical data set obtained in step S1 and the relevant status information set of each employee, including data cleaning and data standardization; S3. Feature extraction is performed on the pre-processed employee historical data set and the relevant status information set of each employee to respectively obtain the task completion amount Rwc, the error amount Cwz, the number of collaborative workers Xzrw of the task to be processed, and the reserved time Ysc of the task to be processed. The task completion amount Rwc is associated with the error amount Cwz to obtain the comprehensive ability coefficient Zhxs of each employee, and the number of collaborative workers Xzrw of the task to be processed is associated with the reserved time Ysc of the task to be processed to obtain the current task complexity coefficient Rfxs of each employee. A convolutional neural network is used to construct a trained resource allocation analysis model, and then the saturation evaluation index Bpzs of the corresponding employee is obtained by fitting the comprehensive ability coefficient Zhxs and the task complexity coefficient Rfxs of the corresponding employee. S3 also includes: S33, according to the relevant status information set, by associating the number of collaborative workers Xzrw of the task to be processed with the reserved time Ysc of the task to be processed, and after linear normalization processing, to obtain the current task complexity coefficient Rfxs of each employee, which is specifically obtained according to the following formula: ; In the formula, Expressed as the number of urgent tasks, , and They are respectively represented by the number of collaborative workers Xzrw for the pending tasks, the reserved time Ysc for the pending tasks, and the number of expedited tasks The weight coefficient of , V is expressed as the correction constant; S3 also includes: S34, by transmitting the task complexity coefficient Rfxs and the comprehensive ability coefficient Zhxs of the corresponding employee to the resource allocation analysis model, and after linear normalization processing, the saturation evaluation index Bpzs of the corresponding employee is obtained, which is specifically obtained according to the following formula: ; In the formula, It is represented by the current pending tasks of the jth employee, Expressed as the task complexity coefficient Rfxs of the jth employee, Expressed as the comprehensive ability coefficient of the jth employee, It is expressed as the mean value of the task processing amount of the jth employee during the monitoring period; S4. Pre-set the balance threshold K, and obtain the imbalance rate Shs by comparing the saturation evaluation index Bpzs of each employee. Compare and analyze the imbalance rate Shs with the balance threshold K to comprehensively judge whether the current human resources are in a balanced state in task scheduling. If not, issue a configuration optimization instruction and take corresponding optimization measures.

2. The method for optimizing human resource allocation according to claim 1, characterized in that: S2 specifically includes the following steps: S21. Detect and delete the repeatedly collected data information to avoid the bias of data duplication on analysis, and identify missing data to detect and repair outliers; S22. Standardize the data processed in step S21 using dimensionless processing technology to eliminate unit and dimension differences in the data.

3. The method for optimizing human resource allocation according to claim 2, characterized in that: S3 specifically includes the following steps: S31. Use convolutional neural networks to preliminarily construct the original model, and train and test the original model with employee historical data sets and related current status information sets. Use the trained original model as a resource identification model, obtain feature information within the resource identification model, and use the obtained feature information to train and test the resource identification model. Use the trained resource identification model as a resource allocation analysis model.

4. The method for optimizing human resource allocation according to claim 3, characterized in that: S3 also includes: S32. Based on the employee historical data set, the task completion amount Rwc and the error amount Cwz are correlated and then subjected to linear normalization processing to calculate and obtain the comprehensive ability coefficient Zhxs of each employee. Specifically, it is obtained according to the following formula: ; In the formula, n represents the number of monitoring periods, i=1, 2, 3, ..., n, It is expressed as the amount of tasks completed in the i-th period, It is expressed as the mean value of the task completion within the monitoring period. It is expressed as the amount of error in the i-th period, It is expressed as the mean value of the error amount within the monitoring period, and are all weight coefficients.

5. The method for optimizing human resource allocation according to claim 4, characterized in that: S4 specifically includes the following steps: S41, using the saturation evaluation index Bpzs of the corresponding employees obtained in step S34, and using a statistical mean algorithm to calculate the mean of the overall employee saturation evaluation index ; S42, based on the average of the overall employee saturation assessment index , and compare it with the saturation evaluation index Bpzs of each employee to determine the degree to which each employee can bear the current task situation, including the following: If the saturation evaluation index Bpzs exceeds the average of the overall employee saturation evaluation index When , the corresponding employee's tolerance to the current task situation will be judged to be in an abnormal state. At this time, the number of employees in the abnormal state Yss will be counted and corresponding records will be made; If the saturation evaluation index Bpzs does not exceed the average of the overall employee saturation evaluation index When the employee's tolerance to the current task is determined to be normal, S43. Calculate the imbalance ratio Shs.

6. The method for optimizing human resource allocation according to claim 1, characterized in that: S4 also includes: S44, presetting a balance threshold K, and comparing and analyzing the balance threshold K with the imbalance rate Shs to comprehensively determine whether the current human resources are in a balanced state in terms of task scheduling, specifically including the following contents: If the imbalance rate Shs ≥ the balance threshold K, it will be comprehensively judged that the current human resources are not in a balanced state in terms of task scheduling, and a configuration optimization instruction will be issued to transfer the tasks to be completed from the employees in the abnormal state to the employees who are not in the abnormal state. At the same time, regular meetings will be held to understand the work status and needs of each employee and adjust the task allocation in time; If the imbalance rate Shs is less than the balance threshold K, it will be comprehensively judged that the current human resources are in a balanced state in terms of task scheduling. At this time, no configuration optimization instructions will be issued to the outside. On the premise of ensuring task balance, the existing task allocation and work arrangements will be maintained, and the task allocation situation will be checked and evaluated regularly.

7. A human resource optimization configuration system, using a human resource optimization configuration method according to any one of claims 1 to 6, characterized in that: It includes data acquisition module, data preprocessing module, resource analysis module and configuration management module; The data collection module extracts the relevant historical record information of each employee from the human resources information system in advance, constructs the employee historical data set, and simultaneously tracks and records the relevant current status information set of each employee, and extracts the relevant complex information of the corresponding assigned tasks according to the relevant current status information set of each employee; The data preprocessing module performs data preprocessing on the acquired employee historical data set and the relevant status information set of each employee, including data cleaning and data standardization processing; The resource analysis module extracts features from the preprocessed employee historical data set and the relevant status information set of each employee to obtain the task completion amount Rwc, the error amount Cwz, the number of collaborative workers Xzrw of the task to be processed, and the reserved time Ysc of the task to be processed, respectively; the task completion amount Rwc is associated with the error amount Cwz to obtain the comprehensive ability coefficient Zhxs of each employee; and the number of collaborative workers Xzrw of the task to be processed is associated with the reserved time Ysc of the task to be processed to obtain the current task complexity coefficient Rfxs of each employee; a convolutional neural network is used to construct a trained resource allocation analysis model; and the saturation evaluation index Bpzs of the corresponding employee is obtained by fitting the comprehensive ability coefficient Zhxs and the task complexity coefficient Rfxs of the corresponding employee; The configuration management module pre-sets a balance threshold K, and obtains the imbalance rate Shs by comparing the saturation evaluation index Bpzs of each employee. The imbalance rate Shs is compared and analyzed with the balance threshold K to comprehensively determine whether the current human resources are in a balanced state in task scheduling. If not, a configuration optimization instruction is issued to the outside and corresponding optimization measures are taken.

Images