Human resource data dynamic processing system based on big data analysis

Abstract

The invention provides a human resource data dynamic processing system based on big data analysis, and relates to the technical field of data processing, and the system comprises a data obtaining module which is used for obtaining team performance data; the initial segmentation module is used for segmenting the employee performance initial sequence; the competitive optimization module is used for carrying out competitive optimization according to the performance of the positive employees; the balance optimization module is used for carrying out balance optimization according to the negative employee performance; the strategy optimization module is used for acquiring a global competition-balance optimization strategy; and the enterprise management module is used for introducing basic training data, performing team planning again, and updating an employee performance initial sequence for dynamic management. The technical problem of poor management efficiency caused by difficulty in capturing dynamic change of employee performance and complex relationship in a team in the prior art can be solved, and the overall management efficiency of an enterprise is improved by combining competitive and balanced optimization and performing layered optimization and dynamic adjustment.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a human resources data dynamic processing system based on big data analysis. Background Art

[0002] In the era of digital economy, data has become the core resource for corporate competition. Enterprises need to analyze and mine various data through big data technology to obtain more value. Human resource management is no exception. Human resource data analysis can help enterprises manage employees more effectively and improve their competitiveness. In current corporate management practices, the analysis of team performance data and the ranking of employee performance are usually based on static data or simple statistical methods. They are unable to deeply explore the complex relationships and potential patterns in the data, and ignore the interactions and influences between team members, as well as the impact of changes in the external environment on performance. Managers cannot accurately identify and solve performance problems, nor can they adjust strategies in time to cope with changes in the market or within the organization.

[0003] In summary, the existing technology has technical problems in that it usually relies on static data or simple statistical methods to perform employee performance ranking and team performance analysis, which makes it difficult to capture the dynamic changes in employee performance and the complex relationships within the team, resulting in poor efficiency in enterprise management. Summary of the invention

[0004] The purpose of this application is to provide a human resources data dynamic processing system based on big data analysis to solve the technical problem that the prior art usually relies on static data or simple statistical methods to perform employee performance ranking and team performance analysis, which makes it difficult to capture the dynamic changes in employee performance and the complex relationships within the team, resulting in poor efficiency in enterprise management.

[0005] In view of the above problems, the present application provides a human resources data dynamic processing system based on big data analysis, wherein the human resources data dynamic processing system based on big data analysis includes: a data acquisition module for acquiring team performance data within a unit time period, ranking the performance of each employee in the same initial team, and obtaining the first an initial sequence of employee performance corresponding to an initial team, wherein i∈[1,t], t is the number of initial teams of the target enterprise; an initial segmentation module, for intercepting M positive initial segments of employee performance and N negative initial segments of employee performance based on the initial sequence of employee performance; a competitive optimization module, for performing competitive optimization with the employee expected goals corresponding to the M positive initial segments of employee performance and the enterprise development training data, and setting a first optimization layer; a balanced optimization module, for performing balanced optimization with the employee expected goals corresponding to the N negative initial segments of employee performance and the team balanced performance data, and setting a second optimization layer; a strategy optimization module, for obtaining the first optimization layer based on the first optimization layer and the second optimization layer. The initial team, Initial team, until The global competition-balance optimization strategy corresponding to the initial team; the enterprise management module is used to simultaneously introduce the basic employee training data, merge the enterprise development training data and the basic employee training data, re-carry out the team planning of the target enterprise, update the initial sequence of employee performance, and generate a global human resources optimization framework in combination with the global competition-balance optimization strategy to dynamically manage the target enterprise.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The data acquisition module is used to obtain team performance data within a unit time period, rank the performance of each employee in the same initial team, and obtain the first an initial sequence of employee performance corresponding to an initial team, wherein i∈[1,t], t is the number of initial teams of the target enterprise; an initial segmentation module, for intercepting M positive initial segments of employee performance and N negative initial segments of employee performance based on the initial sequence of employee performance; a competitive optimization module, for performing competitive optimization with the employee expected goals corresponding to the M positive initial segments of employee performance and the enterprise development training data, and setting a first optimization layer; a balanced optimization module, for performing balanced optimization with the employee expected goals corresponding to the N negative initial segments of employee performance and the team balanced performance data, and setting a second optimization layer; a strategy optimization module, for obtaining the first optimization layer based on the first optimization layer and the second optimization layer. The initial team, Initial team, until The global competition-balance optimization strategy corresponding to the initial team; the enterprise management module is used to simultaneously introduce employee basic training data, merge the enterprise development training data and employee basic training data, re-conduct the team planning of the target enterprise, update the initial sequence of employee performance, and generate a global optimization framework for human resources in combination with the global competition-balance optimization strategy to dynamically manage the target enterprise. In other words, by obtaining team performance data, intercepting positive and negative performance segments, and combining employee expected goals with enterprise training data, a competitive and balanced optimization layer is established, the enterprise development training data is merged with the employee basic training data, and combined with the initial segmentation of employee performance and the global optimization strategy, the team planning and training plan are dynamically updated, thereby improving the overall management efficiency of the enterprise.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0009] Figure 1 This is a schematic diagram of the structure of the human resources data dynamic processing system based on big data analysis in this application; Figure 2 This is a schematic diagram of the global competition-equilibrium optimization strategy flow for the dynamic processing system of human resources data based on big data analysis in this application.

[0010] Explanation of the reference numerals: data acquisition module 11 , initial segmentation module 12 , competition optimization module 13 , balance optimization module 14 , strategy optimization module 15 , enterprise management module 16 . DETAILED DESCRIPTION

[0011] This application provides a human resources data dynamic processing system based on big data analysis, which solves the technical problem that the existing technology usually relies on static data or simple statistical methods to sort employee performance and analyze team performance, which makes it difficult to capture the dynamic changes in employee performance and the complex relationships within the team, resulting in poor efficiency in enterprise management. By obtaining team performance data, intercepting positive and negative performance segments, and combining employee expected goals with enterprise training data, a competitive and balanced optimization layer is established, and enterprise development training data is merged with employee basic training data. Combined with the initial segmentation of employee performance and the global optimization strategy, team planning and training plans are dynamically updated, thereby improving the overall management efficiency of the enterprise.

[0012] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0013] For examples, please see the attached Figure 1 The present application provides a human resources data dynamic processing system based on big data analysis, wherein the human resources data dynamic processing system based on big data analysis includes: The data acquisition module 11 is used to obtain the team performance data within a unit time period, rank the performance of each employee in the same initial team, and obtain the first The initial sequence of employee performance corresponding to the initial teams, where i∈[1,t], t is the initial number of teams in the target enterprise.

[0014] Specifically, within a unit time period (such as a week, month, quarter or year), obtain the performance data of each employee (such as task completion rate, work quality, attendance rate, etc.) from the company's internal human resource management system or other related systems, sort the employees in each team according to their performance, and obtain the initial sequence of employee performance for each initial team. Generate a corresponding initial sequence of employee performance for each chef team of the target company. For example, if the target company has 5 initial teams, 5 such sequences will be obtained, and each sequence corresponds to the performance ranking of all employees in a team. By regularly obtaining team performance data, the company can monitor the performance of the team in real time, which helps to identify high-performing employees and employees who need improvement.

[0015] The initial segmentation module 12 is used to extract M positive employee performance initial segments and N negative employee performance initial segments based on the employee performance initial sequence.

[0016] Specifically, the performance evaluation standard is determined from the human resources database, and the initial sequence of employee performance is intercepted based on the performance evaluation standard. According to the performance evaluation standard, the distance between employees, that is, the difference between employee performance, is calculated. According to various indicators, including performance difference, discrete trend, and performance distribution characteristics, the distance between employees is balanced and adjusted, and the distance difference between some high-performance employees is reduced or increased to ensure that the distance data more accurately reflects the performance difference between employees and the overall distribution characteristics of the team. In the initial sequence of employee performance, M initial segments of positive employee performance that meet the first cluster distribution are intercepted. Similarly, according to various indicators, including performance balance, central tendency, and performance distribution characteristics, the distance between employees is balanced and adjusted, and the distance difference between some low-performance employees is reduced or increased, and the distance between different employees is balanced. The segmentation results are optimized to ensure that the identified negative performance employee group is more in line with expectations when clustering. In the initial sequence of employee performance, N initial segments of negative employee performance that meet the second cluster distribution are intercepted. By intercepting positive and negative performance segments, enterprises can manage employees of different categories more targeted. Rewarding, promoting or developing high-performing employees and training, improving plans or adjusting tasks for low-performing employees ensures that the company can clearly distinguish the performance levels of employees, helps to discover performance differences within the team, optimize resource allocation, and improve overall performance.

[0017] The competitive optimization module 13 is used to perform competitive optimization based on the employee expected goals corresponding to the M positive employee performance initial segments and the enterprise development training data, and set the first optimization layer.

[0018] Specifically, the performance characteristics, advantage areas and improvement space of employees in the M initial performance segments of positive employees are analyzed. The expected goals of employees are determined, including career advancement, leadership enhancement, and expanded scope of responsibility. The expected goals of positive-performing employees often have excellent work ability and potential, and are suitable for further development into the core management or leadership of the enterprise. Provide high-performance employees with enterprise development training data, including leadership-related training courses, including decision-making ability, team management, strategic thinking, etc., as well as corporate goals and development plans. By combining the expected goals of employees and the training data of the enterprise, a competition mechanism is set up to allow positive-performing employees to demonstrate their leadership through competition and incentive mechanisms while participating in training. Through a series of assessments or projects, the enterprise allows employees to demonstrate their abilities in actual management and decision-making, and optimizes the career development path of employees. According to the results of competitive optimization, the first optimization layer, that is, the training of leadership, is set. Through competitive optimization, it is ensured that these high-performing employees are fully developed in leadership, which meets the needs of the enterprise for future management. By combining the expected goals of high-performing employees with the development training resources of the enterprise, the first optimization layer with leadership training as the core is set. Through competitive optimization, companies can not only discover and develop employees with leadership potential, but also ensure that these employees meet the company's long-term strategic needs, thereby laying a solid foundation for the future corporate management team.

[0019] The balance optimization module 14 is used to perform balance optimization based on the employee expected goals corresponding to the N negative employee performance initial segments and the team balanced performance data, and set a second optimization layer.

[0020] Specifically, analyze the initial performance segments of N negative employees and identify the reasons for their poor performance, such as insufficient skills, attitude problems, or resource constraints. According to the analysis results, set improvement goals for these employees, such as improving work skills, improving work attitudes, or enhancing teamwork capabilities. Employees' personal goals may need to be combined with the needs of the company or team to ensure that the career development direction of employees is consistent with the team goals. Collect team balanced performance data, including information such as the overall performance of the team, the efficiency of collaboration between members, and resource allocation. Compare and analyze employees' expected goals with team balanced performance data to determine how to improve employee performance through training, coaching, or adjusting work allocation, thereby improving the performance of the entire team. Help low-performing employees adjust their working methods and task allocation so that they can gradually adapt and integrate into the team, and avoid their performance from dragging down the overall efficiency of the team too much. During the optimization process, the company may provide training, coaching, or strategies to adjust task allocation to help these employees improve their performance. At the same time, by balancing the work allocation within the team, ensure that high-performing employees are not unfairly affected by the performance of negative-performing employees. According to the results of the balance optimization, the second optimization layer is set up to improve the overall performance of the team, especially for employees with poor performance, to ensure balanced performance within the team. By optimizing the balance of the initial performance segments of N negative employees, low-performing employees are helped to gradually improve their work performance while maintaining the overall balance of the team. The introduction of the second optimization layer ensures that the contributions of all employees in the team can be reasonably evaluated and supported, thereby improving the overall efficiency and collaboration of the team.

[0021] The strategy optimization module 15 is used to obtain the first optimization layer and the second optimization layer based on the first optimization layer and the second optimization layer. The initial team, Initial team, until The global competition-balance optimization strategy corresponding to the initial teams.

[0022] Specifically, the first optimization level is mainly aimed at the initial segmentation of positive employee performance, aiming to cultivate leadership and enhance the core competitiveness of the team; the second optimization level is mainly aimed at the initial segmentation of negative employee performance, aiming to improve the overall performance and balance of the team through balanced optimization. The initial team, Initial team, until A comprehensive assessment of the performance, capabilities and potential of the initial team. Integrate multiple first optimization layers, each of which represents an optimization method that drives the team through efficient employees. Integrate multiple first optimization layers through progressive levels to generate a layer of deep channels, so that the optimization results gradually penetrate into the team, ensuring that the entire team structure is always optimized and adjusted around the configuration of efficient employees. Integrate multiple second optimization layers to generate a second-layer deep channel, so that low-performing employees in the team are gradually optimized, ensuring that the alternative combination plays an effective balancing role in the team and supports the smooth operation of the entire team. By connecting the first-layer deep channel (fixed combination led by high-performing employees) and the second-layer deep channel (alternative combination for low-performing employees), a global competition-balance optimization strategy is generated to balance the competitive advantages of high-performing employees and the balanced management of low-performing employees to ensure the maximization of the overall performance of the team. The global competition-balance optimization strategy can not only motivate high-performing employees to continue to contribute, but also ensure the improvement of low-performing employees through alternative combinations, thereby achieving the best effect between competition and balance. Through customized global competition-balance optimization strategies, the overall performance of each team can be significantly improved.

[0023] The enterprise management module 16 is used to simultaneously introduce employee basic training data, merge the enterprise development training data and employee basic training data, re-conduct team planning for the target enterprise, update the initial sequence of employee performance, combine the global competition-balance optimization strategy to generate a global human resources optimization framework, and dynamically manage the target enterprise.

[0024] Specifically, the basic training data of employees is included in the analysis scope, including basic job requirements, operating specifications, initial skills, etc. The enterprise development training data is merged with the basic training data of employees to obtain a comprehensive training record for each employee, and accurately evaluate the potential and development needs of employees. Based on the merged training data, the team structure is replanned, the team structure is adjusted, resources are reallocated, or the combination of team members is updated to ensure that each team has a suitable combination of employees. Highly skilled and high-potential employees can be assigned to positions that require higher responsibility and innovation, while employees with strong basic skills but need further development can receive more targeted tasks and guidance. New team performance goals are set based on the development needs of the enterprise and the capabilities of employees. After the team planning is completed, the initial performance sequence of employees will be re-evaluated according to their new roles and responsibilities to reflect the performance of employees in the new team environment. Using the updated initial performance sequence of employees, combined with the global competition-balance optimization strategy, a new global optimization framework for human resources is generated. According to the optimization framework, specific optimization plans are formulated for different teams and employees, including training plans, career development plans, etc. The global optimization framework of human resources implements the optimization plan into the daily management of the enterprise, dynamically manages the team and employees, continuously monitors the implementation effect of the optimization plan, and makes timely adjustments based on feedback to ensure the effectiveness of human resource management. By introducing basic employee training data and merging it with enterprise development training data, replanning the team and updating the performance sequence, combined with the global competition-balance optimization strategy, a dynamic global optimization framework for human resources is generated, which ensures the rationality of the team structure and can continuously improve the overall operational efficiency and performance of the enterprise through dynamic management.

[0025] Furthermore, the initial segmentation module 12 in the human resources data dynamic processing system based on big data analysis is also used for: Connect to the human resources database and set the performance evaluation standard; based on the employee performance initial sequence and with the performance evaluation standard as a constraint, intercept M positive employee performance initial segments that meet the first cluster distribution; based on the employee performance initial sequence and with the performance evaluation standard as a constraint, intercept N negative employee performance initial segments that meet the second cluster distribution.

[0026] Specifically, the human resources database is connected to obtain relevant employee data from the human resources database, such as attendance records, work performance, quality and quantity of completed tasks, etc. According to the requirements of the enterprise, corresponding performance evaluation standards are formulated, including the employee's completed workload, achieved goals, work efficiency, teamwork ability, feedback from customers or superiors, etc., and weights and scoring standards are set for each indicator to measure the specific work performance of employees. According to the initial sequence of employee performance, the first clustering method is applied for analysis, and the performance evaluation standard is used as a constraint to identify and cluster the employee groups with higher performance, and extract M positive employee performance segments. The performance evaluation standard constraint means that only data that meets the pre-set performance evaluation standard is considered during the analysis. The first cluster distribution refers to a statistical method, such as K-means clustering or hierarchical clustering, to determine which employee performance data can be clustered as positive employees, that is, the highest performance group is grouped together. Through cluster analysis, employees with higher performance are divided into a group, namely, M positive employee performance initial segments.

[0027] Similarly, a second cluster distribution similar to the first cluster distribution is determined, mainly to group the poor-performing employee groups into one group, namely, N initial segments of negative employee performance. Through cluster analysis, the company accurately identifies high-performing and low-performing employee groups, and formulates customized management strategies for employees with different performance levels, such as providing incentives for high-performing employees, providing coaching or training for low-performing employees, and effectively allocating training and development resources to improve overall team performance.

[0028] Furthermore, the initial segmentation module 12 in the human resources data dynamic processing system based on big data analysis is also used for: Based on the initial sequence of employee performance and with the performance evaluation criteria as a constraint, a first distance data set is calculated; at the same time, based on the first distance data set, a distance balance adjustment is performed using a first similarity measurement indicator set of a first cluster distribution association mapping to obtain a second distance data set; based on the second distance data set, M positive initial employee performance segments that satisfy the first cluster distribution are intercepted.

[0029] Specifically, based on the initial sequence of employee performance and the performance evaluation criteria as constraints, the distance between employees is calculated according to the selected distance measurement method, that is, the difference in employee performance is measured. A set of similarity measurement indicators is determined according to the first cluster distribution association mapping, including performance difference characteristics, discrete trend characteristics and performance distribution characteristics, which are used to measure the similarity between employee performance data points. According to the first distance data set and the similarity measurement indicator, the distance balance adjustment is performed, and the distance value is adjusted according to the similarity between the employee performance data points to obtain the second distance data set to solve the imbalance problem in the clustering or highlight specific important features. Using the adjusted second distance data set, M positive employee performance segments that meet the first cluster distribution are intercepted, representing the group of employees with better performance. Through the distance balance adjustment, it is ensured that the selected positive performance segments can better reflect the actual performance of high-performance employees and avoid the deviation caused by relying on a single indicator. Through distance calculation and balance adjustment, the complex differences between employee performance are effectively captured to ensure the accurate identification of high-performance employee groups.

[0030] Furthermore, the initial segmentation module 12 in the human resources data dynamic processing system based on big data analysis is also used for: The first similarity measurement indicator set of the first cluster distribution includes performance difference characteristics, discrete trend characteristics, and performance distribution characteristics; a multi-level balance factor corresponding to the first cluster distribution is added through the performance difference characteristics, discrete degree characteristics, and performance distribution characteristics in the first similarity measurement indicator set; based on the first distance data set, a second distance data set is obtained through the multi-level balance factor corresponding to the first cluster distribution.

[0031] Specifically, the first similarity measurement indicator set of the first cluster distribution includes performance difference characteristics, discrete trend characteristics, and performance distribution characteristics, wherein the performance difference characteristics are used to measure the performance differences between employees to ensure that high-performance and low-performance employees can be accurately identified; the discrete trend characteristics are used to analyze the degree of dispersion of employee performance in the entire team to ensure that employee groups that deviate from mainstream performance are identified and individuals with relatively discrete performance in the team are considered; the performance distribution characteristics are used to reflect the overall distribution of employee performance in the team to ensure that clustering can reflect the overall performance pattern within the team, rather than being limited to individual high or low performance points. The performance difference characteristics, discrete degree characteristics, and performance distribution characteristics in the first similarity measurement indicator set are added to the multi-level balance factor corresponding to the first cluster distribution. The multi-level balance factor is to balance the importance of different performance indicators in cluster analysis. The performance difference characteristic balance factor is a balance adjustment for performance differences to prevent employees with too large differences from affecting the entire clustering result; the discrete trend characteristic balance factor is used to adjust the degree of dispersion to ensure that employees who deviate from normal performance in the team are not ignored; the performance distribution characteristic balance factor is used to ensure the balance of employee performance distribution to avoid extreme situations affecting the overall clustering accuracy.

[0032] On the basis of the first distance data set, by applying multi-level balancing factors, adjusting the distance metric, and optimizing the trade-offs between different characteristics, a more accurate and balanced second distance data set is obtained, ensuring that the distance data more accurately reflects the performance differences between employees and the overall distribution characteristics of the team. By adding multi-level balancing factors, various influencing factors in the cluster distribution are more carefully controlled to ensure that the final clustering results not only reflect individual performance differences, but also take into account the overall performance distribution and discrete trends of the team.

[0033] Furthermore, the initial segmentation module 12 in the human resources data dynamic processing system based on big data analysis is also used for: The second similarity measurement indicator set of the second cluster distribution association mapping includes performance balance characteristics, central tendency characteristics, and performance distribution characteristics; at the same time, based on the first distance data set, the distance balance adjustment is performed using the second similarity measurement indicator set of the second cluster distribution association mapping to obtain a third distance data set; according to the third distance data set, N initial segments of negative employee performance that meet the second cluster distribution are intercepted.

[0034] Specifically, the second similarity measurement indicator set of the second cluster distribution association mapping includes performance balance characteristics, central tendency characteristics, and performance distribution characteristics. Among them, the performance balance characteristic is used to evaluate the balance of employee performance within the team, ensuring that the performance of employees in the negative performance segment is relatively consistent without extreme differences; the central tendency characteristic is used to analyze the concentrated performance of negative-performing employees, usually measured by the mean, median, etc., to determine whether a central tendency is shown in certain performance dimensions, helping managers to better understand the common problems of low-performing employees; the performance distribution characteristic is used to understand the distribution of low-performing employees in the entire team, ensuring that the overall distribution pattern of low-performing employees can be taken into account during clustering, rather than just individual poorly performing employees.

[0035] Through the performance balance, central tendency, and performance distribution characteristics in the second similarity measurement indicator set, the first distance data set is adjusted, and the segmentation results are optimized by balancing the distances between different employees to obtain the third distance data set, ensuring that the identified negative performance employee groups are more in line with expectations when clustering. According to the third distance data set, N employee groups with low performance scores that meet the second cluster distribution are intercepted as N initial segments of negative employee performance, including employee groups with low performance or those that need improvement. Through the clustering method, it helps companies better identify which employees need improvement and formulate corresponding improvement plans. By introducing the second similarity measurement indicator set, the clustering and segmentation of low-performing employees are finely controlled to ensure that the balance and central tendency of low-performing employees within the team can be reasonably identified, which helps companies to carry out targeted management and improvement measures for low-performing employee groups and avoid one-sided evaluation or missing potential problems.

[0036] Furthermore, the strategy optimization module 15 in the human resources data dynamic processing system based on big data analysis is also used for: Through the target enterprise The initial team, Initial team, until The core employee identification of the initial team and the initial segmentation of M positive employee performance are used to set up V team planning fixed combinations; through the first The initial team, Initial team, until The core employee identifications of the initial teams and the initial segmentation of N negative employee performances are used to set up W team planning alternative combinations; based on the team performance contribution, the team planning distribution matrix is ​​set by comparing V team planning fixed combinations and W team planning alternative combinations.

[0037] Specifically, the target enterprise The initial team, Initial team, until Identify the core employees of the initial team to ensure that the key employees who contribute the most to the team's performance can be identified in team planning. Core employees are usually members with strong skills or who undertake important tasks. Match the core employees of each initial team with the employees in the M initial segments of positive employee performance to form a fixed combination of V team plans. This process is a dynamic and iterative process. Each iteration is adjusted according to the new team performance contribution data to gradually optimize the V team planning fixed combinations. As employee performance data is updated and analyzed, the company can continuously adjust the team planning fixed combination to ensure the formation of the best team. The fixed combination represents the standard way for companies to determine the use of high-performance employees as the core and form a team when planning a team. The V team planning fixed combination can ensure the stability and continuous contribution of key employees in the team, help companies establish a team core based on high performance, and improve the overall competitiveness and efficiency of the team.

[0038] Similarly, according to the core employees of each initial team, they are matched with the N initial performance segments of negative employees, and W team planning alternative combinations are set. The alternative combination provides backup plans by flexibly adjusting the roles or responsibilities of low-performing employees, helping companies to make quick adjustments when the team structure is affected. The contribution of the core employees and other members of each team to the overall performance of the team will be evaluated, and the impact of each team member on the success of the team will be quantified, so as to optimize in team planning. Comparing V fixed combinations and W alternative combinations, analysis is conducted based on team performance contribution to see the effects of different team combinations in actual operation, clarify which combinations contribute the most, and which alternative combinations can still maintain good overall performance under low performance conditions. Based on the team performance contribution, the team planning distribution matrix is ​​set up by comparing V fixed combinations and W alternative combinations, and the best performance configuration is found through multiple attempts and optimization. In each round of iteration, the team's planning combination will be adjusted according to the performance contribution, and finally the optimal team structure and configuration will be found to improve the overall performance of the team. Through the identification of core employees and segmentation of employee performance, fixed combinations and alternative combinations are set up respectively, and a team planning distribution matrix is ​​constructed in combination with team performance contribution to help enterprises continuously optimize team structure and achieve efficient management and stable operation.

[0039] Further, as attached Figure 2 As shown, the strategy optimization module 15 in the human resources data dynamic processing system based on big data analysis is also used for: Based on the team planning distribution matrix and the V team planning fixed combination, a layer of deep channel is generated, and the layer of deep channel is obtained by mutual hierarchical integration between multiple first optimization layers; based on the team planning distribution matrix and the W team planning alternative combination, a layer of deep channel is generated, and the layer of deep channel is obtained by mutual hierarchical integration between multiple second optimization layers; the layer of deep channel and the layer of deep channel are connected to generate a global competition-balance optimization strategy with the goal of maximizing team performance.

[0040] Specifically, according to the team planning distribution matrix, combined with V team planning fixed combinations of long-term stable team configurations based on high-performance employees and core employees, a layer of deep channels is generated, which is obtained by integrating the mutual hierarchies between multiple first optimization layers (i.e., optimization layers for initial segmentation of positive employee performance). Each optimization layer of multiple first optimization layers represents an optimization method that drives the team through efficient employees. Hierarchical integration is carried out between the layers to ensure that different optimization methods work together at different levels, so that high-performance employees continue to lead the team to maximize their contributions. Through progressive hierarchical integration of multiple first optimization layers, the optimization results gradually penetrate into the team, ensuring that the entire team structure is always optimized and adjusted around the configuration of efficient employees.

[0041] The team planning distribution matrix is ​​also used in combination with W team planning alternative combinations to generate a two-layer deep channel, which is obtained by integrating the mutual hierarchies between multiple second optimization layers (i.e., the optimization layers for the initial segmentation of negative employee performance). Multiple second optimization layers target low-performing employees and help them integrate into the team and improve their performance through management, task adjustment or training plans without affecting the overall balance of the team. Multiple second optimization layers are integrated at different levels to gradually optimize low-performing employees in the team, ensuring that the alternative combinations play an effective balancing role in the team and support the smooth operation of the entire team.

[0042] Connecting the first-layer deep channel (fixed combination led by high-performing employees) and the second-layer deep channel (alternative combination for low-performing employees) to form a unified optimization framework ensures that the leadership of high-performing employees and the improvement of low-performing employees can work together to improve the performance level of the overall team. Based on the analysis results, a global competition-balance optimization strategy is formulated. This strategy aims to achieve the overall goals of the organization by optimizing the team structure and performance improvement, and to ensure the maximization of the overall performance of the team by balancing the competitive advantages of high-performing employees with the balanced management of low-performing employees. By constructing the first and second layers of deep channels, respectively optimizing high-performing and low-performing employees, and integrating the two, a global competition-balance optimization strategy is formed to maximize team performance. Through hierarchical optimization and deep channel connection, continuous and efficient management and collaboration of corporate teams are achieved.

[0043] Furthermore, the enterprise management module 16 in the human resources data dynamic processing system based on big data analysis is also used for: Based on the human resources global optimization framework, an anomaly identification unit is added, and the anomaly identification unit is used to identify abnormal performance fluctuations and trigger an early warning mechanism; through the early warning mechanism, the dynamic management of the target enterprise is suspended, and the historical global competition-balance optimization strategy is obtained through the human resources database; the stability of the historical global competition-balance optimization strategy is evaluated, and the human resources global optimization framework is updated with the stability satisfying the stability threshold as a constraint.

[0044] Specifically, an abnormal identification unit is added to the global optimization framework of human resources to monitor and identify abnormal fluctuations in employee performance and trigger an early warning mechanism. The abnormal identification unit can identify abnormal fluctuations in performance data, such as a sudden drop or significantly below the average level. When the abnormal identification unit detects abnormal fluctuations in performance, the early warning mechanism is automatically triggered, including sending a notification to management, launching a performance improvement plan, or conducting an in-depth analysis to determine the cause of the problem. When the early warning mechanism is triggered, the dynamic management of the target enterprise is suspended to prevent the abnormal problem from expanding its impact and give managers time and data support to fix the problem. Through the human resources database, retrieve and obtain historical records of global competition-balance optimization strategies implemented in the past, including team planning, employee development plans, performance improvement measures, etc. at different time points, and analyze past solutions and operations. Evaluate the historical global competition-balance optimization strategies obtained, especially the stability of the strategies when facing similar anomalies. Stability evaluation includes analyzing the fluctuations in the effectiveness of the strategy during implementation, its long-term impact, and its adaptability to external changes. Based on the actual situation and goals of the enterprise, a stability threshold is set in advance as a standard for evaluating the stability of the strategy. According to the results of the stability assessment, the global optimization architecture of human resources is updated based on this strategy, and team planning, employee development plans, performance improvement measures, etc. are adjusted to ensure the stability and effectiveness of the architecture. Drawing on past successful experiences, the existing architecture can be kept stable under new abnormal circumstances. After the global optimization architecture is updated and confirmed to be stable, dynamic management is restored to ensure that the human resources management process is not affected in the long term. By introducing an abnormality identification unit, abnormal fluctuations in human resource management are monitored in real time, and the current management operations are suspended through an early warning mechanism to reduce potential risks. Subsequently, historical optimization strategies are analyzed to ensure that their stability meets the threshold before the architecture is updated, ensuring that the efficiency and stability of human resource management are maintained while responding to abnormalities.

[0045] In summary, the human resources data dynamic processing system based on big data analysis provided by this application has the following technical effects: The data acquisition module is used to obtain team performance data within a unit time period, rank the performance of each employee in the same initial team, and obtain the first an initial sequence of employee performance corresponding to an initial team, wherein i∈[1,t], t is the number of initial teams of the target enterprise; an initial segmentation module, for intercepting M positive initial segments of employee performance and N negative initial segments of employee performance based on the initial sequence of employee performance; a competitive optimization module, for performing competitive optimization with the employee expected goals corresponding to the M positive initial segments of employee performance and the enterprise development training data, and setting a first optimization layer; a balanced optimization module, for performing balanced optimization with the employee expected goals corresponding to the N negative initial segments of employee performance and the team balanced performance data, and setting a second optimization layer; a strategy optimization module, for obtaining the first optimization layer based on the first optimization layer and the second optimization layer. The initial team, Initial team, until The global competition-balance optimization strategy corresponding to the initial team; the enterprise management module is used to simultaneously introduce employee basic training data, merge the enterprise development training data and employee basic training data, re-conduct the team planning of the target enterprise, update the initial sequence of employee performance, and generate a global optimization framework for human resources in combination with the global competition-balance optimization strategy to dynamically manage the target enterprise. In other words, by obtaining team performance data, intercepting positive and negative performance segments, and combining employee expected goals with enterprise training data, a competitive and balanced optimization layer is established, the enterprise development training data is merged with the employee basic training data, and combined with the initial segmentation of employee performance and the global optimization strategy, the team planning and training plan are dynamically updated, thereby improving the overall management efficiency of the enterprise.

[0046] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0047] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A human resources data dynamic processing system based on big data analysis, characterized in that: include: The data acquisition module is used to obtain team performance data within a unit time period, rank the performance of each employee in the same initial team, and obtain the first The initial sequence of employee performance corresponding to the initial teams, where i∈[1,t], t is the number of initial teams of the target enterprise; An initial segmentation module, used to extract M positive employee performance initial segments and N negative employee performance initial segments based on the employee performance initial sequence; A competitive optimization module is used to competitively optimize the employee expected goals corresponding to the M initial segments of positive employee performance and the enterprise development training data, and set the first optimization layer; A balance optimization module is used to optimize the balance between the employee expected goals and the team balanced performance data corresponding to the N negative employee performance initial segments, and set the second optimization layer; A strategy optimization module is used to obtain the first optimization layer and the second optimization layer based on the first optimization layer and the second optimization layer. The initial team, Initial team, until The global competition-balance optimization strategy corresponding to the initial teams; The enterprise management module is used to simultaneously introduce employee basic training data, merge the enterprise development training data and employee basic training data, re-conduct team planning for the target enterprise, update the initial sequence of employee performance, combine the global competition-balance optimization strategy to generate a global human resources optimization framework, and dynamically manage the target enterprise.

2. The human resources data dynamic processing system based on big data analysis according to claim 1, characterized in that: Based on the employee performance initial sequence, M positive employee performance initial segments and N negative employee performance initial segments are intercepted, including: Connect to the human resources database and set performance evaluation standards; Based on the employee performance initial sequence and with the performance evaluation standard as a constraint, M positive employee performance initial segments satisfying the first cluster distribution are intercepted; Based on the employee performance initial sequence and with the performance evaluation standard as a constraint, N negative employee performance initial segments satisfying the second cluster distribution are intercepted.

3. The human resources data dynamic processing system based on big data analysis as claimed in claim 2, characterized in that: Based on the employee performance initial sequence and with the performance evaluation standard as a constraint, M positive employee performance initial segments satisfying the first cluster distribution are intercepted, including: Based on the employee performance initial sequence and with the performance evaluation standard as a constraint, calculating a first distance data set; At the same time, based on the first distance data set, a distance balance adjustment is performed using a first similarity measurement indicator set of the first cluster distribution association mapping to obtain a second distance data set; According to the second distance data set, M initial segments of positive employee performance that satisfy the first cluster distribution are intercepted.

4. The human resources data dynamic processing system based on big data analysis as claimed in claim 3, characterized in that: The first similarity measurement indicator set of the first cluster distribution includes performance difference characteristics, discrete trend characteristics, and performance distribution characteristics; Adding a multi-level balance factor corresponding to the first cluster distribution by using the performance difference characteristic, the discrete degree characteristic, and the performance distribution characteristic in the first similarity measurement indicator set; Based on the first distance data set, a second distance data set is obtained through a multi-level balance factor corresponding to the first cluster distribution.

5. The human resources data dynamic processing system based on big data analysis as claimed in claim 4, characterized in that: The second similarity measurement indicator set of the second cluster distribution association mapping includes performance balance characteristics, central tendency characteristics, and performance distribution characteristics; At the same time, based on the first distance data set, a distance balance adjustment is performed using a second similarity measurement indicator set of a second cluster distribution association mapping to obtain a third distance data set; According to the third distance data set, N initial segments of negative employee performance that satisfy the second cluster distribution are intercepted.

6. The human resources data dynamic processing system based on big data analysis according to claim 5, characterized in that: Based on the first optimization layer and the second optimization layer, obtain the The initial team, Initial team, until The global competition-balance optimization strategy corresponding to the initial team includes: Through the target enterprise The initial team, Initial team, until The core employee identification of the initial team and the initial segmentation of M positive employee performances are used to set up V fixed combinations of team planning; Through the target enterprise The initial team, Initial team, until The core employee identification of the initial team and the initial segmentation of N negative employee performances set W team planning alternative combinations; Based on the team performance contribution, the team planning distribution matrix is ​​set up by comparing V team planning fixed combinations and W team planning alternative combinations.

7. The human resources data dynamic processing system based on big data analysis according to claim 6, characterized in that: include: Based on the team planning distribution matrix and the V team planning fixed combinations, a layer of depth channel is generated, where the layer of depth channel is obtained by mutual hierarchical integration between multiple first optimization layers; Based on the team planning distribution matrix and the W team planning alternative combinations, a two-layer depth channel is generated, where the two-layer depth channel is obtained by mutual hierarchical integration between multiple second optimization layers; The first-layer deep channel and the second-layer deep channel are connected to generate a global competition-balance optimization strategy with the goal of maximizing team performance.

8. The human resources data dynamic processing system based on big data analysis according to claim 1, characterized in that: Combined with the global competition-balance optimization strategy, a global human resources optimization framework is generated to dynamically manage the target enterprise, including: Based on the human resources global optimization framework, an abnormality identification unit is added, and the abnormality identification unit is used to identify abnormal performance fluctuations and trigger an early warning mechanism; Through the early warning mechanism, dynamic management of the target enterprise is suspended, and the historical global competition-balance optimization strategy is obtained through the human resources database; The stability of the historical global competition-equilibrium optimization strategy is evaluated, and the human resources global optimization framework is updated with the stability satisfying the stability threshold as a constraint.

Images