Search

CN-121998598-A - Management system and method for enterprise management

CN121998598ACN 121998598 ACN121998598 ACN 121998598ACN-121998598-A

Abstract

The invention relates to the field of enterprise management, in particular to a management system and a management method for enterprise management, which are used for solving the problems of lack of risk early warning capability, low emergency response efficiency, insufficient human capital toughness and rigidification of an assessment mechanism of the existing enterprise management system; the enterprise management system comprises a data acquisition module, an AI risk early warning module, a human capital toughness module, an intelligent emergency response module, a dynamic assessment module and a data decision module which are connected in a communication mode, wherein the modules are cooperatively linked to realize the whole-flow management and control including but not limited to sudden off-duty and emergency leave-leave occasional events of staff.

Inventors

  • YAO SHUWEI

Assignees

  • 青岛人才在线服务管理有限公司

Dates

Publication Date
20260508
Application Date
20260128

Claims (10)

  1. 1. The management system for enterprise management is characterized by comprising a data acquisition module, an AI risk early warning module, a human capital toughness module, an intelligent emergency response module, a dynamic assessment module and a data decision module which are connected in a communication manner, wherein the modules are cooperatively linked to realize the full-flow management and control of sudden off-duty and emergency leave-leave incidents of staff; The data acquisition module is used for integrating and standardizing employee multidimensional behaviors and investigation data and synchronizing the multidimensional behaviors and investigation data to each association module; The AI risk early warning module generates employee departure risk portraits and carries out grading early warning through a trained machine learning model, and captures high-risk behaviors to trigger instant early warning; The human capital toughness module constructs a key post succession plan, a skill matrix and an elastic working pool, so that human talent redundancy management and flexible scheduling are realized; When an abrupt off-duty event is detected, the intelligent emergency response module automatically generates a handover list, recommends an optimal receiver, dynamically distributes tasks and supplements personnel gaps; the dynamic assessment module configures a nonresistance adjustment rule and automatically adapts and adjusts assessment indexes of affected staff; The data decision module identifies sudden off-duty high-frequency trigger factors, generates team health reports and management optimization suggestions, and provides data support for management strategy adjustment.
  2. 2. The management system for enterprise management according to claim 1, wherein the AI risk early warning module comprises an abnormal behavior recognition unit, a model training unit and an early warning pushing unit, wherein the abnormal behavior recognition unit is used for capturing non-card-punching and non-approval records of 3 or more continuous days, downloading key project documents in batches, suddenly reducing work output by 30% or more, suddenly reducing cooperative behavior frequency by 50% or more and other high-risk behaviors in real time and triggering instant early warning, the model training unit adopts a random forest algorithm, trains based on historical behavior data and departure data of more than 5000 employees, and the early warning pushing unit pushes risk early warning information to corresponding responsible persons through a system message, enterprise WeChat/spike linkage pushing mode, and clearly warns about the level, the cause of early warning and preliminary intervention suggestions.
  3. 3. The system of claim 1, wherein the key post successor program in the human capital toughness module adopts a 1-2-1 backup mechanism, namely 1 direct successor, 2 potential candidates and 1 set of standardized handover document templates, wherein the direct successor needs to have more than 3 years of same post working experience, can quickly pick up post core work, the potential candidates need to have 1-2 years of related post working experience, and are systematically cultivated by the direct successor, the standardized handover document templates cover post core responsibilities, workflows, task lists, key document addresses, clients, partner information and the like, and the department responsible person is required to update the successor program and the handover templates once every quarter, and the system automatically reminds updating.
  4. 4. The management system for enterprise management according to claim 1, wherein the intelligent emergency response module comprises a handover list generation unit, a receiver matching unit, a load balancing unit and an elastic recruitment linkage unit, wherein the handover list generation unit can automatically extract all work data related to staff, rank tasks according to emergency degree and importance degree to generate an editable standardized handover list, the receiver matching unit calculates a matching score with the current load (weight 0.4) through skill matching degree (weight 0.6) to recommend 1-2 receivers with the highest score, the load balancing unit calculates the work load saturation of each member of a team in real time, when the saturation exceeds 80%, the task allocation of the member is automatically stopped, the task is allocated to the member with the saturation lower than 60%, and the elastic recruitment linkage unit can automatically push the work demands to the staff meeting the post skill requirements in an elastic recruitment pool and synchronously feed back the response conditions.
  5. 5. The system for enterprise management according to claim 1, wherein the dynamic assessment module comprises an assessment rule configuration unit, an index adjustment unit and an assessment result verification unit, wherein the assessment rule configuration unit supports a manager to define emergency types (including emergency leave, emergency leave and unreliability events), assessment exemption conditions (including task completion rate indexes of an emergency leave-in period exceeding 7 days) and weighting coefficients (including weighting coefficients of all team assessment indexes under unreliability events to be adjusted by 5% -15%), the index adjustment unit receives event trigger signals of the intelligent emergency response module, automatically matches the corresponding adjustment rules to complete exemption or weighting adjustment of the assessment indexes, and the assessment result verification unit is used for verifying the adjusted assessment results to ensure no logic errors and synchronously generate assessment adjustment instructions for follow-up.
  6. 6. The management system for enterprise management according to claim 1, wherein the data decision module comprises a root cause analysis unit, a team health evaluation unit and an optimization suggestion generation unit, wherein the root cause analysis unit correlates historical risk data and behavior data of sudden off-duty staff with enterprise management data through a correlation analysis algorithm, identifies high-frequency trigger factors of sudden off-duty staff including management style, salary competitiveness, working pressure, occupation development space and the like, the team health evaluation unit generates 0-100 points of team health score based on core indexes such as active off-duty rate, emergency leave frequency, key post vacancy duration and talent redundancy, and the optimization suggestion generation unit outputs targeted management optimization suggestions including recruitment standard adjustment, training plan optimization, excitation mechanism improvement and relay plan optimization specific measures according to the root cause analysis result and the team health score.
  7. 7. A management method for enterprise management, characterized in that it is implemented based on the management system for enterprise management according to any one of claims 1-6, and comprises the following steps: s1, integrating employee attendance data, work output data, cooperative behavior data and off-job trend investigation data through a data acquisition module, cleaning, de-duplicating and standardizing various data, removing invalid data and abnormal data, ensuring data accuracy, and synchronizing the standardized data after processing to an AI risk early warning module and a data decision module; S2, the AI risk early warning module carries out multidimensional analysis on the received standardized data through a trained machine learning model, generates employee departure risk portraits, carries out hierarchical early warning according to three levels of low, medium and high, captures employee high-risk behaviors in real time through an abnormal behavior recognition unit, triggers instant early warning, pushes early warning information to corresponding responsible persons, and a manager intervenes according to the early warning information; S3, building a key post '1-2-1' succession plan, a visual skill matrix and a dynamic elastic recruitment pool through a human capital toughness module, updating staff skill information, a succession person culture progress and elastic recruitment resource information in real time, checking and updating the key post succession plan every quarter, and ensuring sufficient talent reservation; S4, when an employee sudden off-duty event is detected, the intelligent emergency response module automatically extracts core work information of the employee, a standardized handover list is generated, an optimal receiver is calculated and recommended through the receiver matching unit, the linkage load balancing unit completes task dynamic allocation, if a personnel gap exists, replacement personnel are matched from an elastic recruitment pool through the elastic recruitment linkage unit, and normal business propulsion is ensured; S5, the dynamic assessment module receives the emergency information transmitted by the intelligent emergency response module, and the assessment index of the affected staff is automatically exempted or weighted by matching the corresponding assessment adjustment rule through the index adjustment unit, and after the assessment result verification unit verifies that the assessment index is error-free, an assessment adjustment description is generated, so that the assessment fairness is ensured; S6, the data decision module receives the operation data of each module, identifies the high-frequency trigger factors of sudden off-duty through the root cause analysis unit, generates a team health report through the team health evaluation unit, combines the two to output targeted management optimization suggestions, the enterprise management layer adjusts the management strategy according to the optimization suggestions, simultaneously feeds back the complex disc data to the AI risk early warning module, optimizes the model training effect, and forms closed loop iteration.
  8. 8. The method for enterprise management according to claim 7, wherein in the AI risk assessment and early warning step, a random forest algorithm is adopted by a machine learning model to perform weighted calculation on behavior characteristics, wherein an attendance anomaly ratio is 15%, a work output fluctuation ratio is 25%, a collaboration activity ratio is 20%, an off-job tendency investigation data ratio is 20%, other behavior characteristics ratio is 20%, the accuracy of identifying high risk off-job by the model is not less than 92%, and an AUC value is 0.89, so that the method has good generalization capability and can adapt to demands of enterprises of different scales and industries.
  9. 9. The method for managing enterprises according to claim 7, wherein in the intelligent emergency handling step, the calculation formula of the catcher's matching score is that the matching score = skill matching degree x 0.6+ (1-current workload saturation) ×0.4, wherein the skill matching degree is calculated by the coincidence degree of the staff skill label and the post demand label, the value range is 0-1, the current workload saturation is calculated by the staff task waiting number, the task emergency degree and the estimated completion time length, the value range is 0-1, and when the matching score is more than or equal to 0.8, the catcher is recommended to be the optimal catcher.
  10. 10. The method for managing enterprises according to claim 7, wherein in the data multiplexing iteration step, a team health report is generated once in a quarter, and the team health report comprises core indexes such as active departure rate, emergency leave frequency, key post vacancy duration, talent redundancy, early warning accuracy and the like, meanwhile, the AI risk early warning model is retrained once every half year, latest employee behavior data and departure data are integrated, the early warning accuracy of the model is continuously improved, the succession plan and skill matrix of the human capital toughness module are comprehensively optimized once each year, and the enterprise business development requirements are adapted.

Description

Management system and method for enterprise management Technical Field The invention relates to the field of enterprise management, in particular to a management system and a management method for enterprise management. Background Along with the deep digital transformation of enterprises, various enterprise management systems are widely applied to the scenes of personnel organization, project cooperation, performance assessment and the like. The existing system generally has the functions of basic attendance approval, flow diversion and report statistics, part of the system introduces a machine learning algorithm to quantitatively evaluate staff performance, but is limited to single-dimension data statistics and analysis, and a full-flow risk prevention and control and emergency disposal system is not formed. In the aspect of human capital management, the main flow scheme focuses on static information recording of the whole life cycle of staff, basic talent checking is realized through a post instruction book and a skill label, a normalized talent redundancy reserve and dynamic scheduling mechanism is lacked, when dealing with personnel abnormal movement, the management strategy is optimized by relying on indexes such as manually triggering a handover flow, manually distributing subsequent work tasks, analyzing the departure rate through post statistics, and the like, quick response and active intervention of emergency situations cannot be realized, and the continuity of enterprise business cannot be guaranteed. However, the prior art still has the following defects The existing system can only passively receive leave-leave or leave-job applications submitted by staff, potential sudden off-duty risks cannot be actively identified through multidimensional behavior data, a standardized risk assessment model is not built, hierarchical early warning cannot be conducted on staff off-duty trends, an enterprise is caused to sink into the passive state when key post staff leave the off-duty suddenly, service continuity is difficult to guarantee, and losses such as project delay and key information loss are easily caused. In the face of sudden off-duty events, the conventional system relies on manual work to complete operations such as working handover list establishment, catcher matching, task redistribution and the like, lacks intelligent handover list generation, optimal catcher recommendation and team load dynamic balancing mechanisms, has complicated handover process and long time consumption, is easy to cause key information loss and project delay, and cannot quickly make up for personnel gaps. The conventional system does not establish a normalized key post succession plan and skill redundancy mechanism, does not establish a visual skill matrix and a dynamic talent pool, cannot grasp team skill coverage conditions and talent reserve conditions in real time, and when core personnel leave the post, enterprises cannot quickly match replacement personnel from an internal talent pool or external elastic talent resources, so that service faults are caused, and a systematic cultivation and tracking mechanism for a relay is lacked. The existing assessment tool adopts a fixed index system, can not dynamically adjust special conditions such as sudden leave, unreliability and the like, is not provided with flexible assessment exemption and weighting adjustment rules, is easy to cause the disjoint of the assessment result and the actual contribution of staff, influences the satisfaction degree of the staff and the stability of the staff, and can aggravate the active job departure risk of the staff. Disclosure of Invention In order to overcome the technical problems, the invention aims to provide a management system and a management method for enterprise management, which are used for solving the problems of lack of risk early warning capability, low emergency response efficiency, insufficient human capital toughness and rigidification of an assessment mechanism of the existing enterprise management system provided by the background art. The aim of the invention can be achieved by the following technical scheme: A management system for enterprise management comprises a data acquisition module, an AI risk early warning module, a human capital toughness module, an intelligent emergency response module, a dynamic assessment module and a data decision module which are in communication connection, wherein the modules are cooperatively linked to realize full-flow management and control of sudden off-duty and emergency leave-leave incidents of staff; The data acquisition module is used for integrating and standardizing employee multidimensional behaviors and investigation data and synchronizing the multidimensional behaviors and investigation data to each association module; The AI risk early warning module generates employee departure risk portraits and carries out grading early warning through a trained machine learning model,