Lever succession prediction and employment decision recommendation method and device, electronic equipment and storage medium

Abstract

The invention provides a cadre succession prediction and employment decision recommendation method and device, an electronic device and a storage medium, and belongs to the technical field of human resource management, in the method, multi-source data is considered, and quantitative prediction can be performed on post vacancy probability, talent loss risk and succession matching degree, so that early warning is realized, and the labor intensity is reduced. According to the process, early warning can be carried out in advance, the succession recommendation scheme is obtained through data driving and does not depend on subjective experience of HR, human intervention is reduced, and the method is more scientific.

Description

Technical Field

[0001] This invention relates to the technical field of human resource management, and in particular to a method, apparatus, electronic device, and storage medium for predicting cadre succession and recommending personnel for decision-making. Background Technology

[0002] In today's organizational management landscape, companies are increasingly relying on systematic, data-driven talent management methods. However, traditional talent profiling and risk identification solutions generally suffer from the following problems: One-dimensional role perspective: Most systems rely solely on employee data (such as performance ratings and attendance records), neglecting the behavior and judgment of multiple roles, including HRBPs and business supervisors, in the talent management process. Insufficient predictive capabilities: Lack of quantitative predictions on job vacancy probability, talent loss risk, and succession matching.

[0003] In summary, traditional talent profiling and risk identification solutions suffer from technical problems such as a single role perspective and insufficient predictive capabilities. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, apparatus, electronic device and storage medium for predicting cadre succession and recommending personnel decisions, so as to alleviate the technical problems of traditional talent profile construction and risk identification schemes having a single role perspective and insufficient predictive ability.

[0005] In a first aspect, embodiments of the present invention provide a method for predicting cadre succession and recommending personnel for decision-making, including: Acquire multi-source data, wherein the sources of the multi-source data include: HR system data, 360 assessment results, and organizational structure relationships; The job vacancy probability model is used to predict the job vacancy probability of the job feature vectors in the multi-source data, and the vacancy probability of each job is obtained. The talent turnover probability model is used to predict the talent turnover probability of the employee feature vectors in the multi-source data, and the turnover probability of each employee is obtained. The succession matching degree model is used to perform succession matching calculation on the employee job map in the multi-source data to obtain the succession matching score between employees and jobs; The warning level is determined based on the vacancy probability of each position, the turnover probability of each employee, and the succession matching score between the employee and the position. Determine the successor recommendation scheme corresponding to the warning level.

[0006] Furthermore, the job feature vector includes: the age of the job manager, the length of service of the job manager, the historical turnover frequency of the job, the importance of the job, and the organizational level; The job vacancy probability model includes: ,in, Indicates job position In time The probability of a subsequent vacancy event. Indicates the baseline cumulative risk. This represents the weight vector obtained during training. This represents the feature vector of the job position.

[0007] Furthermore, the employee feature vector includes: the average performance of the most recent 12 months, the total score of competency matching, training frequency, frequency of changes in supervisors, and number of attendance anomalies; The talent loss probability model includes: ,in, Indicates employees In time The probability of resignation within the company. This represents the cumulative output of all decision trees. , Represents the weights of the XGBoost model. Indicates bias. This represents the employee feature vector.

[0008] Furthermore, the employee job graph includes: employee nodes, job nodes, and edges between nodes, whereby the edges represent relationships between nodes; The succession matching degree model includes: ,in, Indicates employees With position The successor matching score, Indicates employees pass Feature representation after propagation in a multi-layered GNN Indicates job position pass Feature representation after propagation in a multilayer GNN.

[0009] Furthermore, the warning level is determined based on the vacancy probability of each position, the turnover probability of each employee, and the succession matching score between the employee and the position, including: If the probability of vacancy for the target position is greater than the first preset threshold, or the probability of turnover for the target employee is greater than the second preset threshold and the succession matching score between the target employee and the position is less than the third preset threshold, then the warning level is determined to be a high-risk level. If the probability of vacancy for the target position is greater than the fourth preset threshold but not greater than the first preset threshold, or the probability of employee turnover is greater than the fifth preset threshold but not greater than the second preset threshold, then the warning level is determined to be a medium-risk level.

[0010] Furthermore, determining the successor recommendation scheme corresponding to the warning level includes: If the warning level is a high-risk level, then for the target position corresponding to the high-risk level, output the list of the top preset number of employees with the highest successor matching score for the target position.

[0011] Furthermore, determining the successor recommendation scheme corresponding to the warning level also includes: If the warning level is medium risk, then a training plan with a preset duration will be developed.

[0012] Secondly, embodiments of the present invention also provide a cadre succession prediction and personnel decision recommendation device, comprising: The acquisition unit is used to acquire multi-source data, wherein the sources of the multi-source data include: HR system data, 360 assessment results, and organizational structure relationships; The job vacancy probability prediction unit is used to predict the job vacancy probability of the job feature vector in the multi-source data using the job vacancy probability model, so as to obtain the vacancy probability of each job. The talent loss probability prediction unit is used to predict the talent loss probability of each employee by using the talent loss probability model to analyze the employee feature vectors in the multi-source data. The succession matching calculation unit is used to perform succession matching calculation on the employee job map in the multi-source data using the succession matching degree model, and obtain the succession matching score of employees and jobs. The first determining unit is used to determine the warning level based on the vacancy probability of each position, the turnover probability of each employee, and the succession matching score between the employee and the position. The second determining unit is used to determine the successor recommendation scheme corresponding to the warning level.

[0013] Thirdly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in any of the first aspects above.

[0014] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing machine-executable instructions, which, when invoked and executed by a processor, cause the processor to perform the method described in any of the first aspects above.

[0015] In this embodiment of the invention, a method for predicting cadre succession and recommending personnel decisions is provided, comprising: acquiring multi-source data, wherein the sources of multi-source data include: HR system data, 360 assessment results, and organizational structure relationships; using a job vacancy probability model to predict the job vacancy probability of the job feature vectors in the multi-source data, thereby obtaining the vacancy probability of each job; using a talent loss probability model to predict the talent loss probability of the employee feature vectors in the multi-source data, thereby obtaining the loss probability of each employee; using a succession matching degree model to perform succession matching calculation on the employee-job map in the multi-source data, thereby obtaining the succession matching score between employees and jobs; determining an early warning level based on the vacancy probability of each job, the loss probability of each employee, and the succession matching score between employees and jobs; and determining a succession recommendation scheme corresponding to the early warning level. As described above, the cadre succession prediction and personnel decision recommendation method of the present invention considers multi-source data and can quantitatively predict the probability of job vacancies, the risk of talent loss, and the succession matching degree, thereby achieving early warning and providing succession recommendation schemes corresponding to the warning level. The above process can provide early warning, and the succession recommendation scheme is obtained through data-driven means, without relying on the subjective experience of HR, reducing human intervention, making it more scientific, and alleviating the technical problems of traditional talent profile construction and risk identification schemes having a single role perspective and insufficient predictive ability. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating a method for predicting cadre succession and recommending personnel for decision-making, provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a cadre succession prediction and personnel decision recommendation device provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Traditional talent profiling and risk identification solutions suffer from limited perspectives and insufficient predictive capabilities.

[0020] Based on this, the cadre succession prediction and personnel decision recommendation method of the present invention considers multi-source data and can quantitatively predict the probability of job vacancies, the risk of talent loss, and the succession matching degree, thereby achieving early warning and providing succession recommendation schemes corresponding to the warning level. The above process can provide early warning, and the succession recommendation scheme is obtained through data-driven means, without relying on the subjective experience of HR, reducing human intervention and making it more scientific.

[0021] To facilitate understanding of this embodiment, a method for predicting cadre succession and recommending personnel for decision-making will be described in detail first.

[0022] Example 1: According to an embodiment of the present invention, an embodiment of a method for predicting cadre succession and recommending personnel for decision-making is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0023] Figure 1 This is a flowchart of a method for predicting cadre succession and recommending personnel for decision-making, according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps: Step S102: Obtain multi-source data, including HR system data, 360 assessment results, and organizational structure relationships. Specifically, the aforementioned multi-source data comes from the cadre management system. HR system data, 360 assessment results, and organizational structure relationships are all part of the cadre management system.

[0024] Step S104: Use the job vacancy probability model to predict the job vacancy probability of the job feature vector in the multi-source data, and obtain the vacancy probability of each job. Step S106: Use the talent loss probability model to predict the talent loss probability of the employee feature vectors in the multi-source data, and obtain the loss probability of each employee. Step S108: Use the succession matching degree model to perform succession matching calculation on the employee job map in the multi-source data to obtain the succession matching score between employees and jobs. Step S110: Determine the warning level based on the vacancy probability of each position, the turnover probability of each employee, and the succession matching score between employees and positions. Step S112: Determine the recommended successor scheme corresponding to the warning level.

[0025] In this embodiment of the invention, a method for predicting cadre succession and recommending personnel decisions is provided, comprising: acquiring multi-source data, wherein the sources of multi-source data include: HR system data, 360 assessment results, and organizational structure relationships; using a job vacancy probability model to predict the job vacancy probability of the job feature vectors in the multi-source data, thereby obtaining the vacancy probability of each job; using a talent loss probability model to predict the talent loss probability of the employee feature vectors in the multi-source data, thereby obtaining the loss probability of each employee; using a succession matching degree model to perform succession matching calculation on the employee-job map in the multi-source data, thereby obtaining the succession matching score between employees and jobs; determining an early warning level based on the vacancy probability of each job, the loss probability of each employee, and the succession matching score between employees and jobs; and determining a succession recommendation scheme corresponding to the early warning level. As described above, the cadre succession prediction and personnel decision recommendation method of the present invention considers multi-source data and can quantitatively predict the probability of job vacancies, the risk of talent loss, and the succession matching degree, thereby achieving early warning and providing succession recommendation schemes corresponding to the warning level. The above process can provide early warning, and the succession recommendation scheme is obtained through data-driven means, without relying on the subjective experience of HR, reducing human intervention, making it more scientific, and alleviating the technical problems of traditional talent profile construction and risk identification schemes having a single role perspective and insufficient predictive ability.

[0026] The above provides a brief overview of the cadre succession prediction and personnel decision-making recommendation method of the present invention. The specific details involved are described in detail below.

[0027] In an optional embodiment of the present invention, The job characteristic vector includes: the age of the job manager, the length of service of the job manager, the historical turnover frequency of the job, the importance of the job, and the organizational level; Job vacancy probability models include: ,in, Indicates job position In time The probability of a subsequent vacancy event. Indicates the baseline cumulative risk. This represents the weight vector obtained during training. This represents the feature vector of a job position.

[0028] Specifically, establish a job-level survival analysis model to quantitatively predict the future survival of specific jobs over a given period of time. The probability of a vacancy appearing inside. This provides data support for succession planning.

[0029] The modeling approach is as follows: data preparation → survival function construction → Cox model training → probability calculation.

[0030] Data preparation: Input data: Job feature vector =[Job supervisor's age, job supervisor's tenure, job turnover frequency, job importance, organizational level]; Survival time data: Observation period: Records of changes in job supervisors over the past N months; Define the event: =Actual departure time of the person in charge (excluding deleted data).

[0031] Survival function definition: Survival function: ,in, Represents the survival function, job position In time The probability that no vacancy event will occur afterward. Indicates survival time, job position The length of time from the start of the observation period to the departure of the person in charge (when the vacancy occurs). Indicates the time span of the forecast (e.g., the probability of a job opening within the next 6 months). Indicates job position Survival time exceeds The probability, from 0 to The integral represents the calculation of the cumulative risk from the observation point to time t. Indicates a point in time ,post Given features The instantaneous vulnerability risk rate. Survival function. Through risk function The integral definition of risk reflects long-term cumulative risk. When the risk function... When it increases, Decays faster (increased probability of vacancy). Feature Its function is to influence the risk rate through the Cox model: ,in, This represents the nonparametric baseline risk function (computed using the Breslow estimator). The weight vector to be trained (dimension) d ×1).

[0032] post In time The probability of a subsequent vacancy event: .

[0033] Cox proportional hazards model: Risk function: ,in, This represents the nonparametric baseline risk function (computed using the Breslow estimator). The weight vector to be trained (dimension) d ×1).

[0034] Weight estimation: During training, the partial likelihood function is: ,in, =1 (event occurred) or 0 (right censoring). Indicates in The risk set at any given moment (the set of positions still in operation).

[0035] Log-likelihood: .

[0036] Vacancies probability calculation: Cumulative risk function: ,in, Indicates the baseline cumulative risk. , express Event count at any given moment.

[0037] Final vacancy probability: This formula is the core expression of the job vacancy probability model, built upon the Cox proportional hazards model (survival analysis), and is used to quantify job vacancy rates. In the future The probability of a vacancy occurring within a time period. It is obtained through nonparametric estimation of job vacancy events from historical data (such as the Breslow estimator), reflecting the average risk accumulation trend without considering job characteristics. This indicates the impact of a feature, specifically its amplification / reduction effect on the baseline risk. Weighting of (e.g., the age of the person in charge) If the value is greater than 0, increasing the value of this feature will increase the probability of a missing feature.

[0038] In an optional embodiment of the present invention, the employee feature vector includes: the average performance of the most recent 12 months, the total score of competency matching, the training frequency, the frequency of changes in superiors, and the number of attendance exceptions; The probability model for talent loss includes: ,in, Indicates employees In time The probability of resignation within the company. This represents the cumulative output of all decision trees. , Represents the weights of the XGBoost model. Indicates bias. This represents the employee feature vector.

[0039] Specifically, the problem is defined as follows: Objective: To predict employee numbers In the future Probability of leaving the company within a month .

[0040] Tag definition: ; Constructing employee feature vectors ; annotation (Observation period) t Prepare sample data (records of resignations within the past month).

[0041] Model selection and formula: Logistic Regression outputs the probability formula: , ,in, Represents the employee feature vector. Represents the weights of the XGBoost model. Indicates bias.

[0042] Loss function (Binary Cross-Entropy):

[0043] XGBoost (Gradient Boosting Tree): Output probability formula: Predicting probabilities by integrating multiple decision trees: , This represents the cumulative output value of all decision trees.

[0044] Loss function: Custom weighted cross-entropy: ,in, Indicates the weights of positive samples (used to handle class imbalance), weighted training: =Number of negative samples / Number of positive samples, Logistic Regression: Gradient Descent Optimization In and .

[0045] In an optional embodiment of the present invention, the employee job graph includes: employee nodes, job nodes, and edges between nodes, where the edges represent the relationships between the nodes. Succession matching models include: ,in, Indicates employees With position The successor matching score, Indicates employees pass Feature representation after propagation in a multi-layered GNN Indicates job position pass Feature representation after propagation in a multilayer GNN.

[0046] Specifically, the graph structure is defined as: organization graph G=(V,E).

[0047] Node set V: ; Edge set E: Edge types include: Employee-Position (Current): This indicates the employee's current position. Employee-Position (History): This indicates the positions the employee has held. Employee-Employee (Referral Relationship) indicates a nomination relationship between HRBP / supervisor; Employee-Employee (Mentor Relationship) refers to the mentor-student relationship in a talent development program; Employee Node Feature vectors (feature standardization: all numerical features need to be normalized to [0,1]): ,in, Indicates the average performance. Indicates skill rating. Indicates training frequency. This indicates the attendance anomaly rate.

[0048] Job Node Feature vectors: ,in, Indicates the importance of the position (levels 1-5). This indicates job category embedding (e.g., one-hot).

[0049] GNN propagation layer: The update formula for the k-th layer node is: ,in, Represents a node The neighborhood group, Represents aggregate functions (such as mean, maximum, or LSTM). , This represents the trainable parameter matrix and bias terms. This represents the ReLU activation function.

[0050] Successor matching score calculation: Cosine similarity formula: The successor matching score is ∈ [0,1], and the closer it is to 1, the higher the matching degree.

[0051] In an optional embodiment of the present invention, the warning level is determined based on the vacancy probability of each position, the turnover probability of each employee, and the succession matching score between employees and positions, specifically including the following steps: (1) If the vacancy probability of the target position is greater than the first preset threshold, or the turnover probability of the target employee is greater than the second preset threshold and the succession matching score of the target employee and the position is less than the third preset threshold, then the warning level is determined to be a high-risk level. (2) If the vacancy probability of the target position is greater than the fourth preset threshold but not greater than the first preset threshold, or the employee turnover probability is greater than the fifth preset threshold but not greater than the second preset threshold, then the warning level is determined to be medium risk level.

[0052] Specifically, the early warning logic is defined as follows: Based on the probability of job vacancies Employee turnover rate Succession matching score for employees and positions Based on a comprehensive assessment, a three-level early warning signal is output: ,in, Indicates a high-risk level. Indicates a medium-risk level. This indicates a low-risk level.

[0053] In an optional embodiment of the present invention, determining the successor recommendation scheme corresponding to the warning level specifically includes the following steps: (1) If the warning level is high risk level, output the list of the top 10 employees with the highest successor matching score for the target position corresponding to the high risk level. (2) If the warning level is medium risk level, then formulate a training plan with a preset duration.

[0054] Specifically, after outputting red, yellow, and green warning signals, the system needs to perform the following actions to achieve closed-loop management: Warning signal push: Real-time notifications to HRBPs, line managers and senior executives, automatically triggered reminders via WeChat / email / system dashboard; Succession plan generation: For positions under red alert, automatically generate a Top-K list of successors (based on...). (Sorted), with a matching analysis report attached; Recommended intervention measures: Red alert: Initiate an emergency succession plan (such as job replacement, cross-departmental transfer); Yellow alert: Develop a 3-6 month training plan (such as mentorship, project experience); Green alert: Regular monitoring (such as quarterly review).

[0055] This invention addresses three core issues in cadre succession management through AI technology: Insufficient risk foresight: Traditional methods passively respond to job vacancies or talent loss; this invention predicts risks 6-12 months in advance (red, yellow, and green early warnings), reserving a decision-making window; Decision-making is highly subjective: traditional methods rely on HR experience and are easily influenced by biases; this invention uses data-driven recommendations (such as matching quantified scores) to reduce human intervention. Inefficient training: Traditional methods use generic training that is not tailored to specific job requirements; this invention is based on... Personalized development plans are generated to address capability gaps (such as a special enhancement program for "strategic thinking plus financial analysis").

[0056] Final result: At the organizational level: Reduce the vacancy period for key positions (from an average of 45 days to 15 days); In terms of talent: the success rate of succession for high-potential employees increased by 40% (through precise matching); Cost-wise: Reduce external recruitment costs (increase the proportion of internal succession from 30% to 70%).

[0057] Example 2: This invention also provides a cadre succession prediction and personnel appointment recommendation device, which is mainly used to execute the cadre succession prediction and personnel appointment recommendation method provided in Embodiment 1 of this invention. The following is a detailed description of the cadre succession prediction and personnel appointment recommendation device provided in this invention.

[0058] Figure 2 This is a schematic diagram of a cadre succession prediction and personnel decision recommendation device according to an embodiment of the present invention, such as... Figure 2 As shown, the device mainly includes: an acquisition unit 10, a job vacancy probability prediction unit 20, a talent loss probability prediction unit 30, a succession matching calculation unit 40, a first determination unit 50, and a second determination unit 60, wherein: The acquisition unit is used to acquire multi-source data, which includes HR system data, 360 assessment results, and organizational structure relationships. The job vacancy probability prediction unit is used to predict the job vacancy probability from the job feature vectors in multi-source data using a job vacancy probability model, and obtain the vacancy probability of each job. The talent turnover probability prediction unit is used to predict the talent turnover probability of employees in multi-source data by using the talent turnover probability model to obtain the turnover probability of each employee. The succession matching calculation unit is used to perform succession matching calculations on the employee job map in multi-source data using a succession matching degree model, and obtain the succession matching score between employees and jobs. The first determining unit is used to determine the warning level based on the vacancy probability of each position, the turnover probability of each employee, and the succession matching score between employees and positions. The second determining unit is used to determine the recommended successor scheme corresponding to the warning level.

[0059] In this embodiment of the invention, a device for predicting cadre succession and recommending personnel decisions is provided, comprising: acquiring multi-source data, wherein the sources of the multi-source data include: HR system data, 360 assessment results, and organizational structure relationships; using a job vacancy probability model to predict the job vacancy probability of the job feature vectors in the multi-source data, thereby obtaining the vacancy probability of each job; using a talent loss probability model to predict the talent loss probability of the employee feature vectors in the multi-source data, thereby obtaining the loss probability of each employee; using a succession matching degree model to perform succession matching calculation on the employee job map in the multi-source data, thereby obtaining the succession matching score between employees and jobs; determining an early warning level based on the vacancy probability of each job, the loss probability of each employee, and the succession matching score between employees and jobs; and determining a succession recommendation scheme corresponding to the early warning level. As described above, the cadre succession prediction and personnel decision recommendation device of the present invention considers multi-source data and can quantitatively predict the probability of job vacancies, the risk of talent loss, and the succession matching degree, thereby achieving early warning and providing succession recommendation schemes corresponding to the warning level. The above process can provide early warning, and the succession recommendation scheme is obtained through data-driven means, without relying on the subjective experience of HR, reducing human intervention, making it more scientific, and alleviating the technical problems of traditional talent profile construction and risk identification schemes having a single role perspective and insufficient predictive ability.

[0060] Optionally, the job feature vector includes: the age of the job manager, the job manager's length of service, the job's historical turnover frequency, the job's importance, and the organizational level; the job vacancy probability model includes: ,in, Indicates job position In time The probability of a subsequent vacancy event. Indicates the baseline cumulative risk. This represents the weight vector obtained during training. This represents the feature vector of a job position.

[0061] Optionally, the employee feature vector includes: the average performance over the past 12 months, the total competency matching score, training frequency, the frequency of supervisor changes, and the number of attendance anomalies; the talent turnover probability model includes: ,in, Indicates employees In time The probability of resignation within the company. This represents the cumulative output of all decision trees. , Represents the weights of the XGBoost model. Indicates bias. This represents the employee feature vector.

[0062] Optionally, the employee job graph includes: employee nodes, job nodes, and edges between nodes, where edges represent relationships between nodes; the succession matching model includes: ,in, Indicates employees With position The successor matching score, Indicates employees pass Feature representation after propagation in a multi-layered GNN Indicates job position pass Feature representation after propagation in a multilayer GNN.

[0063] Optionally, the first determining unit is further configured to: determine the warning level as high-risk if the vacancy probability of the target position is greater than the first preset threshold, or the turnover probability of the target employee is greater than the second preset threshold and the succession matching score of the target employee and the position is less than the third preset threshold; and determine the warning level as medium-risk if the vacancy probability of the target position is greater than the fourth preset threshold but not greater than the first preset threshold, or the turnover probability of the employee is greater than the fifth preset threshold but not greater than the second preset threshold.

[0064] Optionally, the second determining unit is also used to: if the warning level is a high-risk level, output a list of the top preset number of employees with the highest successor matching scores for the target positions corresponding to the high-risk level; if the warning level is a medium-risk level, formulate a training plan with a preset duration.

[0065] The device provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0066] like Figure 3 As shown in the figure, an electronic device 600 provided in this application includes: a processor 601, a memory 602 and a bus. The memory 602 stores machine-readable instructions that can be executed by the processor 601. When the electronic device is running, the processor 601 and the memory 602 communicate through the bus. The processor 601 executes the machine-readable instructions to perform the steps of the cadre succession prediction and personnel decision recommendation method described above.

[0067] Specifically, the aforementioned memory 602 and processor 601 can be general-purpose memory and processor, without any specific limitations. When the processor 601 runs the computer program stored in the memory 602, it can execute the aforementioned method for predicting cadre succession and recommending personnel for decision-making.

[0068] The processor 601 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 601 or by instructions in software form. The processor 601 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 602, and processor 601 reads the information from memory 602 and, in conjunction with its hardware, completes the steps of the above method.

[0069] Corresponding to the above-mentioned method for predicting cadre succession and recommending personnel, this application also provides a computer-readable storage medium storing machine-executable instructions. When the machine-executable instructions are called and run by a processor, the machine-executable instructions cause the processor to perform the steps of the above-mentioned method for predicting cadre succession and recommending personnel.

[0070] The cadre succession prediction and personnel decision recommendation device provided in this application embodiment can be specific hardware on a device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0071] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0072] For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0073] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0074] In addition, the functional units in the embodiments provided in this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0075] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the cadre succession prediction and personnel decision recommendation method described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0077] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for predicting cadre succession and recommending personnel for decision-making, characterized in that, include: Acquire multi-source data, wherein the sources of the multi-source data include: HR system data, 360 assessment results, and organizational structure relationships; The job vacancy probability model is used to predict the job vacancy probability of the job feature vectors in the multi-source data, and the vacancy probability of each job is obtained. The talent turnover probability model is used to predict the talent turnover probability of the employee feature vectors in the multi-source data, and the turnover probability of each employee is obtained. The succession matching degree model is used to perform succession matching calculation on the employee job map in the multi-source data to obtain the succession matching score between employees and jobs; The warning level is determined based on the vacancy probability of each position, the turnover probability of each employee, and the succession matching score between the employee and the position. Determine the successor recommendation scheme corresponding to the warning level.

2. The method according to claim 1, characterized in that, The job feature vector includes: age of the job manager, length of service of the job manager, historical turnover frequency of the job, importance of the job, and organizational level; The job vacancy probability model includes: ,in, Indicates job position In time The probability of a subsequent vacancy event. Indicates the baseline cumulative risk. This represents the weight vector obtained during training. This represents the feature vector of the job position.

3. The method according to claim 1, characterized in that, The employee feature vector includes: average performance over the past 12 months, total competency matching score, training frequency, frequency of changes in supervisors, and number of attendance anomalies. The talent loss probability model includes: ,in, Indicates employees In time The probability of resignation within the company. This represents the cumulative output of all decision trees. , Represents the weights of the XGBoost model. Indicates bias. This represents the employee feature vector.

4. The method according to claim 1, characterized in that, The employee job graph includes: employee nodes, job nodes, and edges between nodes, where the edges represent the relationships between nodes. The successor matching degree model includes: ,in, Indicates employees With position The successor matching score, Indicates employees pass Feature representation after propagation in a multi-layered GNN Indicates job position pass Feature representation after propagation in a multilayer GNN.

5. The method according to claim 1, characterized in that, The warning level is determined based on the vacancy probability of each position, the turnover probability of each employee, and the succession matching score between the employee and the position, including: If the probability of vacancy for the target position is greater than the first preset threshold, or the probability of turnover for the target employee is greater than the second preset threshold and the succession matching score between the target employee and the position is less than the third preset threshold, then the warning level is determined to be a high-risk level. If the probability of vacancy for the target position is greater than the fourth preset threshold but not greater than the first preset threshold, or the probability of employee turnover is greater than the fifth preset threshold but not greater than the second preset threshold, then the warning level is determined to be a medium-risk level.

6. The method according to claim 1, characterized in that, Determining the successor recommendation scheme corresponding to the warning level includes: If the warning level is a high-risk level, then for the target position corresponding to the high-risk level, output the list of the top preset number of employees with the highest successor matching score for the target position.

7. The method according to claim 1, characterized in that, Determining the successor recommendation scheme corresponding to the warning level also includes: If the warning level is medium risk, then a training plan with a preset duration will be developed.

8. A device for predicting cadre succession and recommending personnel for decision-making, characterized in that, include: The acquisition unit is used to acquire multi-source data, wherein the sources of the multi-source data include: HR system data, 360 assessment results, and organizational structure relationships; The job vacancy probability prediction unit is used to predict the job vacancy probability of the job feature vector in the multi-source data using the job vacancy probability model, so as to obtain the vacancy probability of each job. The talent loss probability prediction unit is used to predict the talent loss probability of each employee by using the talent loss probability model to analyze the employee feature vectors in the multi-source data. The succession matching calculation unit is used to perform succession matching calculation on the employee job map in the multi-source data using the succession matching degree model, and obtain the succession matching score of employees and jobs. The first determining unit is used to determine the warning level based on the vacancy probability of each position, the turnover probability of each employee, and the succession matching score between the employee and the position. The second determining unit is used to determine the successor recommendation scheme corresponding to the warning level.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores machine-executable instructions that, when invoked and executed by a processor, cause the processor to perform the method according to any one of claims 1 to 7.

Images