Enterprise data processing system and method based on large model

Abstract

The invention relates to the technical field of enterprise management, and discloses an enterprise data processing system and method based on a large model, and the method comprises the steps: obtaining corresponding Q pieces of intermediate personnel structure data according to initial personnel structure data and Q personnel adjustment strategies, then calculating a personnel flow value according to personnel change data, traversing the Q pieces of intermediate personnel structure data, and carrying out the calculation of the flow value according to the personnel flow value. Future personnel structure data is obtained through prediction according to the intermediate personnel structure data and the personnel flow value, finally, a structure risk value is calculated according to the future personnel structure data, and Q personnel adjustment strategies are optimized based on the structure risk value and a preset intelligent optimization algorithm. The future personnel structure data is predicted through the personnel flow value and the intermediate personnel structure data, the problem that the personnel structure is difficult to dynamically predict in the prior art is solved, the personnel adjustment strategy is optimized based on the structure risk value, potential risks caused by personnel flow are effectively avoided, the enterprise management efficiency is improved, and resource configuration is optimized.

Description

Technical Field

[0001] The present invention relates to the field of enterprise management technology, and more specifically, to an enterprise data processing system and method based on a large model. Background Art

[0002] Enterprise internal control regulates business activities and risk management through systems, processes and measures, improves management efficiency and enhances core competitiveness. It can not only prevent risks, but also respond to external changes and promote enterprise development. With the advancement of data, intelligent computing and information technology, internal control will continue to be optimized with the support of management concepts and big data technology. For example, a reasonable personnel structure can significantly improve operational efficiency and optimize resource allocation.

[0003] In the prior art, the patent with publication number CN111178664A provides a control method, system, server and medium for enterprise management dimension. The patent realizes centralized information management by collecting basic information, assessment events and evaluation information of employees, storing them in the employee information database, and performing consistency check on the project information uploaded by technical personnel. If the degree of consistency reaches the preset value, it is associated. If it does not match, the difference information is output for the manager to handle. The patent with publication number CN115526605A provides an approval method and system based on enterprise internal control management. The patent analyzes paper application documents through image acquisition, extracts keywords and approval information, and matches the workflow and job responsibility data corresponding to the keyword analysis results based on the enterprise internal control management parameters; the approval results are finally determined by combining the approval information and matching results.

[0004] Although existing technologies have explored the use of big data and other technologies for internal corporate control, they mainly focus on the control and optimization of corporate information processes, and rarely involve the management and adjustment of the internal personnel structure of the enterprise. This limitation makes it difficult for enterprises to achieve dynamic prediction and reasonable adjustment of personnel structure when faced with situations with high personnel mobility or complex personnel structure. At the same time, they are also unable to effectively identify and avoid potential risks caused by personnel mobility.

[0005] In view of this, the present invention proposes an enterprise data processing system and method based on a big model to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides an enterprise data processing system and method based on a large model.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] In a first aspect, a method for processing enterprise data based on a large model is provided, comprising:

[0009] Obtaining initial personnel structure data and Q personnel adjustment strategies of the target enterprise, and obtaining corresponding Q intermediate personnel structure data according to the initial personnel structure data and the Q personnel adjustment strategies, wherein the initial personnel structure data includes initial age structure data, initial personnel ratio data, and initial job distribution data;

[0010] Obtain the target company's personnel change data, calculate the personnel turnover value based on the personnel change data, traverse Q intermediate personnel structure data, and predict the future personnel structure data based on the intermediate personnel structure data and the personnel turnover value;

[0011] The structural risk value is calculated according to the future personnel structure data, and Q personnel adjustment strategies are optimized based on the structural risk value and the preset intelligent optimization algorithm to obtain the optimal adjustment strategy.

[0012] Furthermore, the personnel change data includes the number of employees joining, the number of employees leaving, and the number of employees transferring. The method for calculating the personnel turnover value based on the personnel change data includes:

[0013] According to the personnel change data, a corresponding personnel change matrix is ​​constructed, and the personnel change matrix is ​​multiplied element by element with the preset weight matrix to obtain a weighted change matrix, and the personnel flow value is determined based on the weighted change matrix.

[0014] Furthermore, the weighted change matrix includes:

[0015] WCM= ;

[0016] Among them, WCM is represented as a weighted change matrix, Characterized as The number of employees joining each department, Characterized as The number of employees leaving the department, Characterized as Number of employee transfers per department, Characterized as The weight corresponding to the number of employees joining each department, Characterized as The weight corresponding to the number of employees leaving each department, Characterized as The weight corresponding to the number of employee transfers in each department.

[0017] Furthermore, the method for determining the staff turnover value based on the weighted change matrix includes:

[0018] FLV= ;

[0019] In the formula, FLV is the personnel turnover value, Indicates The department in The weighted change value under the change type, Indicates Total number of employees leaving the department, All are weight factors, and the change types include employee joining, employee leaving and employee transfer.

[0020] Furthermore, the method for predicting future personnel structure data based on the intermediate personnel structure data and the personnel turnover value includes:

[0021] Input the intermediate personnel structure data and personnel flow values ​​into the pre-built structure prediction model to obtain the future personnel structure data;

[0022] The construction method of the structural prediction model includes:

[0023] A training sample set is obtained, which includes historical intermediate personnel structure data and historical personnel flow values, and preset sliding steps and sliding window lengths; the training sample set is converted into multiple training samples using a sliding window method, and the training samples are used as inputs of the initial model, and the historical intermediate personnel structure data after the predicted sliding steps are used as outputs of the initial model. The subsequent historical intermediate personnel structure data of each training sample is used as a prediction target, and the initial model is trained with prediction accuracy as a training target; a structural prediction model is generated that predicts future personnel structure data based on the intermediate personnel structure data and personnel flow values.

[0024] Furthermore, the future personnel structure data includes future age structure data, future personnel ratio data and future job distribution data. The method for calculating the structural risk value based on the future personnel structure data includes:

[0025] The age groups, positions and departments in the future personnel structure data are taken as nodes, and the future age structure data, future personnel proportion data and future position distribution data are taken as edges to construct a personnel structure diagram. The Herfindahl-Hirschman index and Shannon entropy value of the personnel structure diagram are calculated, and the difference between the Herfindahl-Hirschman index and the Shannon entropy value is taken as the structural risk value.

[0026] Furthermore, the intelligent optimization algorithm is a whale optimization algorithm, which optimizes Q personnel adjustment strategies based on the structural risk value and the preset intelligent optimization algorithm. The method for obtaining the optimal adjustment strategy includes:

[0027] S301: Define the initial number of whales as Q and the maximum number of iterations , each initial whale individual is represented as a personnel adjustment strategy, and the random value rand is a random number sampled from a uniform distribution of [0, 1];

[0028] S302: Obtain the structural risk value corresponding to the personnel adjustment strategy, and use the structural risk value as the target fitness value of the initial whale individual;

[0029] S303: When the random value rand is less than 0.5, a shrinking and encircling strategy is performed; when the random value rand is greater than or equal to 0.5, a spiral hunting strategy is performed;

[0030] S304: Repeat the above step S303 to continuously update the personnel adjustment strategy until the maximum number of iterations is reached , output the current optimal personnel adjustment strategy, and take the optimal personnel adjustment strategy as the optimal adjustment strategy.

[0031] Furthermore, the method of implementing the shrinking and surrounding strategy includes:

[0032] ;

[0033] in, For the next generation of whale positions, is the current whale position, To pursue the target location, is the shrinkage coefficient of the shrinkage and encirclement strategy, is the control factor of the shrinking and encircling strategy, is the current iteration number.

[0034] In a second aspect, a big model-based enterprise data processing system is provided, which is used to implement the above-mentioned big model-based enterprise data processing method, including:

[0035] Data processing module: used to obtain the initial personnel structure data and Q personnel adjustment strategies of the target enterprise, and obtain the corresponding Q intermediate personnel structure data according to the initial personnel structure data and the Q personnel adjustment strategies, wherein the initial personnel structure data includes initial age structure data, initial personnel ratio data and initial job distribution data;

[0036] Structure prediction module: used to obtain the personnel change data of the target enterprise, calculate the personnel turnover value based on the personnel change data, traverse Q intermediate personnel structure data, and predict the future personnel structure data based on the intermediate personnel structure data and the personnel turnover value;

[0037] Strategy optimization module: used to calculate the structural risk value according to the future personnel structure data, and optimize Q personnel adjustment strategies based on the structural risk value and the preset intelligent optimization algorithm to obtain the optimal adjustment strategy.

[0038] According to a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned large model-based enterprise data processing method when executing the computer program.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention first obtains corresponding Q intermediate personnel structure data according to the initial personnel structure data and Q personnel adjustment strategies, then calculates the personnel flow value according to the personnel change data, traverses the Q intermediate personnel structure data, and obtains the future personnel structure data according to the intermediate personnel structure data and the personnel flow value prediction, and finally calculates the structural risk value according to the future personnel structure data, and optimizes the Q personnel adjustment strategies based on the structural risk value and a preset intelligent optimization algorithm. In this way, the present invention predicts the future personnel structure data through the personnel flow value and the intermediate personnel structure data, solves the problem of the difficulty in dynamically predicting the personnel structure in the prior art, optimizes the personnel adjustment strategy based on the structural risk value, and effectively avoids the potential risks caused by personnel mobility, which not only improves the enterprise management efficiency, but also optimizes the resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flowchart of a method for processing enterprise data based on a large model in the present invention;

[0042] Figure 2 It is a structural schematic diagram of an enterprise data processing system based on a large model in the present invention;

[0043] Figure 3 It is a flow chart of the method for calculating the personnel turnover value according to the personnel change data in the present invention;

[0044] Figure 4 The figure is a schematic diagram of the structure of an electronic device in the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Example 1

[0047] See also Figure 1 As shown, this embodiment discloses a method for processing enterprise data based on a big model, including:

[0048] S10: Obtaining initial personnel structure data and Q personnel adjustment strategies of the target enterprise, and obtaining corresponding Q intermediate personnel structure data according to the initial personnel structure data and the Q personnel adjustment strategies, wherein the initial personnel structure data includes initial age structure data, initial personnel ratio data, and initial job distribution data;

[0049] In this embodiment, the initial personnel structure data represents the current human resource composition and distribution of the target enterprise, the initial age structure data refers to the proportion of employees of different age groups in the total number of employees, the initial personnel proportion data refers to the proportion of employees of each department in the target enterprise in the total number of employees, and the initial position distribution data refers to the distribution ratio of the number of employees in each position in the target enterprise in the total number of employees. The above-mentioned age groups can be divided according to the same interval, for example, with every 10 years as an interval, employees are divided into age groups such as 20-30 years old, 30-40 years old, 40-50 years old, 50-60 years old, etc., so as to intuitively reflect the distribution ratio of different age groups in the enterprise. It can be understood that different types of target enterprises will result in different departments under the target enterprises, which can be determined according to actual conditions. Similarly, different types of target enterprises will lead to different position types, and this embodiment does not limit this.

[0050] It should be noted that the personnel adjustment strategy refers to a series of plans or measures for optimizing or adjusting the internal personnel structure of the target enterprise, including but not limited to personnel deployment, job adjustment, employee training and recruitment plans, etc., to meet the development needs of the enterprise or solve problems in the existing personnel structure. It is understandable that Q personnel adjustment strategies are pre-planned through expert experience. Different personnel adjustment strategies will lead to different degrees of changes in the personnel structure of the target enterprise, and may cause differences in age distribution, department proportion and job distribution, which will directly affect the enterprise's resource allocation efficiency, operating costs and adaptability to future development needs. Therefore, it is necessary to optimize the personnel adjustment strategy to minimize the risk of personnel structure and ensure the stability and flexibility of the enterprise in human resource management.

[0051] S20: Obtain the personnel change data of the target enterprise, calculate the personnel turnover value according to the personnel change data, traverse Q intermediate personnel structure data, and predict the future personnel structure data according to the intermediate personnel structure data and the personnel turnover value;

[0052] In this embodiment, the personnel change data includes but is not limited to the number of employees joining, the number of employees leaving, and the number of employees transferred. It should be noted that the number of employees joining refers to the number of employees who have signed formal labor contracts or short-term employment agreements with the target enterprise and started to perform their job responsibilities, the number of employees leaving refers to the number of employees who have left due to contract termination, retirement, etc., and the number of employees transferred includes the number of employees whose positions have been adjusted due to transfer, promotion or demotion. In the above, taking the number of employees joining as an example, the number of employees joining can be the average number of employees joining in recent months, so as to reflect the recruitment stability and human resource replenishment efficiency of the target enterprise within a certain time period. Similarly, the average number of employees leaving in recent months can be taken to reflect the staff turnover rate and resignation trend of the target enterprise within a certain time period; for the number of employee transfers, the average number of employee transfers in recent months can be taken to reflect the frequency of internal position adjustment and the flexibility of personnel flow of the target enterprise.

[0053] like Figure 3 As shown, the method for calculating the personnel turnover value based on the personnel change data includes:

[0054] According to the personnel change data, a corresponding personnel change matrix is ​​constructed, and the personnel change matrix is ​​multiplied element by element with the preset weight matrix to obtain a weighted change matrix, and the personnel flow value is determined based on the weighted change matrix.

[0055] Exemplarily, the staff change matrix is ​​as follows;

[0056] PCM= ;

[0057] Among them, PCM is represented as a personnel change matrix, Characterized as The number of employees joining each department, Characterized as The number of employees leaving the department, Characterized as The number of employee transfers per department.

[0058] Then, the weighted change matrix is ​​as follows;

[0059] WCM= ;

[0060] Among them, WCM is represented as a weighted change matrix, Characterized as The weight corresponding to the number of employees joining each department, Characterized as The weight corresponding to the number of employees leaving each department, Characterized as The weight corresponding to the number of employee transfers in each department.

[0061] Methods for determining staff turnover values ​​based on a weighted change matrix include:

[0062] FLV= ;

[0063] In the formula, FLV is the personnel turnover value, Indicates The department in The weighted change value under the change type, Indicates Total number of employees leaving the department, All are weight factors, and the change types include employee joining, employee leaving and employee transfer.

[0064] For example, if If is 3, the weighted change matrix is ​​as follows;

[0065] WCM= ;

[0066] In this embodiment, if is 1, If is 2, for .

[0067] It should be noted that the staff turnover value represents the overall staff turnover of the target enterprise within a certain period of time due to changes such as personnel entry, resignation and transfer. The larger the staff turnover value, the more frequent the staff changes in the target enterprise, which means that the staff stability within the enterprise is lower.

[0068] Methods for predicting future personnel structure data based on intermediate personnel structure data and personnel turnover values ​​include:

[0069] The intermediate personnel structure data and personnel flow values ​​are input into the pre-built structure prediction model to obtain the future personnel structure data.

[0070] The construction method of the structural prediction model includes:

[0071] Obtain a training sample set, which includes historical intermediate personnel structure data and historical personnel flow values, and preset sliding steps and sliding window lengths; convert the training sample set into multiple training samples using a sliding window method, use the training samples as the input of the initial model, predict the historical intermediate personnel structure data after the sliding step as the output of the initial model, use the subsequent historical intermediate personnel structure data of each training sample as the prediction target, and use the prediction accuracy as the training target to train the initial model; generate a structural prediction model that predicts future personnel structure data based on the intermediate personnel structure data and personnel flow values, and the initial model is an LSTM model;

[0072] It should be noted that the sliding window method is a conventional technical means of the LSTM model, and the present invention will not be further explained in principle here; however, in order to facilitate the implementation of the present invention, the present invention provides the following example of the sliding window method:

[0073] Assume that we want to use historical data [1,2,3,4,5,6] to train an LSTM model. In this embodiment, we take the prediction time step as 1 as an example, set the sliding step to 1, and set the sliding window length to 3; then three groups of training samples and corresponding prediction target data are generated: [1,2,3], [2,3,4], and [3,4,5] as training samples, and [4], [5], and [6] as prediction targets respectively;

[0074] The prediction accuracy can be measured using mean square error or mean absolute error as the loss function, and the weights and biases of the model are updated through the back-propagation algorithm to generate a structural prediction model.

[0075] In this embodiment, the future personnel structure data represents the composition and distribution of human resources of the target enterprise after a certain period of time, predicted based on the current intermediate personnel structure data and personnel turnover values, including the proportion of employees of different age groups in the future, the proportion of employees in each department in the total number of employees, and the distribution ratio of the number of employees in each position in the total number of employees, etc. Therefore, this embodiment can dynamically reflect the actual personnel turnover of the target enterprise by introducing personnel change data and calculating personnel turnover values ​​on the basis of obtaining the current personnel structure data of the target enterprise and formulating personnel adjustment strategies, so that the intermediate personnel structure data can be combined with the personnel turnover characteristics. This combination realizes the transition from static personnel structure analysis to dynamic mobility assessment, thereby providing more accurate and comprehensive data support for subsequent prediction of future personnel structure based on personnel turnover.

[0076] S30: Calculate the structural risk value according to the future personnel structure data, and optimize the Q personnel adjustment strategies based on the structural risk value and the preset intelligent optimization algorithm to obtain the optimal adjustment strategy;

[0077] The future personnel structure data include future age structure data, future personnel proportion data and future job distribution data. The future age structure data refers to the proportion of employees of different age groups in the total number of employees of the target enterprise at the predicted time point, reflecting the trend and changes in the age distribution of the enterprise in the future. The future personnel proportion data refers to the proportion of employees of each department in the total number of employees of the target enterprise at the predicted time point, reflecting the personnel distribution of each department in the future enterprise. The future job distribution data refers to the distribution ratio of the number of employees in each position in the total number of employees of the target enterprise at the predicted time point, reflecting the allocation of human resources in job settings of the future enterprise.

[0078] Methods for calculating structural risk values ​​based on future personnel structure data include:

[0079] The age groups, positions and departments in the future personnel structure data are taken as nodes, and the future age structure data, future personnel proportion data and future position distribution data are taken as edges to construct a personnel structure diagram. The Herfindahl-Hirschman index and Shannon entropy value of the personnel structure diagram are calculated, and the difference between the Herfindahl-Hirschman index and the Shannon entropy value is taken as the structural risk value.

[0080] It should be noted that the future age structure data, future personnel ratio data and future job distribution data are all used as edges. When constructing the personnel structure diagram, the future age structure data, future personnel ratio data and future job distribution data are used to represent the relationship weights between nodes (i.e., the attribute values ​​of the edges), which are explained as follows by taking an example:

[0081] There are three types of edges in the personnel structure diagram, including: age group-department, department-position and age group-position:

[0082] Age group-sector represents the proportion of employees of a certain age group in a particular department;

[0083] Department-position represents the proportion of employees in each position in a department;

[0084] Age group-position represents the proportion of employees of a certain age group in a specific position.

[0085] In the above, the Herfindahl-Hirschman index is an indicator for measuring the concentration of distribution. In this embodiment, the Herfindahl-Hirschman index represents the concentration of the future personnel structure of the target enterprise. The Shannon entropy value is an indicator for measuring the uncertainty or diversity of the system distribution. In this embodiment, the Shannon entropy value represents the diversity and balance of the future personnel structure of the target enterprise. The larger the Herfindahl-Hirschman index, the higher the concentration of the future personnel structure of the target enterprise, that is, certain age groups, departments or positions account for too large a proportion, and the distribution is too concentrated, which may lead to an imbalance in resource allocation and excessive dependence on specific nodes, thereby increasing management risks. The larger the Shannon entropy value, the higher the diversity and balance of the future personnel structure of the target enterprise, that is, the distribution of each age group, department or position is more uniform, the resource allocation is more reasonable, and the system flexibility is stronger. Therefore, the calculation of the Herfindahl-Hirschman index and the Shannon entropy value is a prior art, and this embodiment will not go into too much detail.

[0086] Therefore, from the above content, it can be seen that in this embodiment, the larger the structural risk value, the more concentrated the distribution of the target enterprise's future personnel structure is and the less diverse it is, that is, the proportion of certain age groups, departments or positions is too concentrated, resulting in an imbalance in resource allocation and prominent single-position problems, and may have an adverse impact on the enterprise's management flexibility and adaptability, thereby increasing future management risks and the difficulty of optimizing the personnel structure.

[0087] The intelligent optimization algorithm is the whale optimization algorithm. Based on the structural risk value and the preset intelligent optimization algorithm, the Q personnel adjustment strategies are optimized. The method for obtaining the optimal adjustment strategy includes:

[0088] S301: Define the initial number of whales as Q and the maximum number of iterations , each initial whale individual is represented as a personnel adjustment strategy, and the random value rand is a random number sampled from a uniform distribution of [0, 1];

[0089] This embodiment provides a variety of initial solutions for the algorithm by initializing Q whales. This diversity helps to improve the global search capability of the algorithm and avoid falling into the local optimal solution. The random value rand is used to allocate opportunities for different strategies, so that the algorithm can balance the capabilities of local search (contraction) and global search (spiral hunting).

[0090] S302: Obtain the structural risk value corresponding to the personnel adjustment strategy, and use the structural risk value as the target fitness value of the initial whale individual;

[0091] It can be understood that the structural risk value corresponds to the "fitness value" in the whale optimization algorithm, which represents the "survival ability" of an individual in the entire group. In the whale optimization algorithm, each individual (whale) has a fitness value to measure the quality of the individual. The smaller the fitness value, the closer the individual is to the optimal solution.

[0092] S303: When the random value rand is less than 0.5, a shrinking and encircling strategy is performed; when the random value rand is greater than or equal to 0.5, a spiral hunting strategy is performed;

[0093] Among them, the shrinking and encircling strategy is implemented, and the whale will shrink and encircle around the optimal solution. The spiral hunting strategy is implemented to simulate the whale moving around the target in a spiral path.

[0094] S304: Repeat the above step S303 to continuously update the personnel adjustment strategy until the maximum number of iterations is reached , output the current optimal personnel adjustment strategy, and take the optimal personnel adjustment strategy as the optimal adjustment strategy.

[0095] In this embodiment, in each iteration, the whale group is continuously updated until the maximum number of iterations is reached. After each iteration, the algorithm will update the weight factor combination of individual whales and calculate the new fitness value. Through repeated iterations, the weight factor combination of individual whales is gradually improved each time, so that the whale group gradually approaches the optimal solution.

[0096] Methods for implementing the shrinking and encircling strategy include:

[0097] ;

[0098] in, For the next generation of whale positions, is the current whale position, To pursue the target location, is the shrinkage coefficient of the shrinkage and encirclement strategy, is the control factor of the shrinking and encircling strategy, is the current iteration number.

[0099] This embodiment allows individual whales to gradually shrink when approaching the optimal solution, accurately adjust the weight factor, and perform local optimization. Through this strategy, individual whales gradually approach the current optimal solution, ensuring a detailed search in the solution space.

[0100] Methods for conducting a spiral hunting strategy include:

[0101] = ;

[0102] in, is the spiral contraction coefficient of the spiral hunting strategy, A random value in the range [-1, 1].

[0103] This embodiment obtains personnel change data and calculates personnel flow values ​​through step S20, dynamically reflects the actual personnel flow characteristics of the target enterprise, and then combines the operation of calculating the structural risk value according to the future personnel structure data in step S30 and optimizing the personnel adjustment strategy. It can realize the full-link management from dynamic evaluation of personnel flow to accurate quantification of structural risks and then to strategy optimization. This combination can ensure that the optimized personnel adjustment strategy is in line with the actual trend of future personnel flow of the enterprise, and can effectively avoid potential structural risks, thereby enhancing the stability and flexibility of the enterprise in human resource management, and at the same time providing a strong guarantee for the rationality of resource allocation and future development.

[0104] This embodiment first obtains corresponding Q intermediate personnel structure data based on the initial personnel structure data and Q personnel adjustment strategies, then calculates the personnel flow value based on the personnel change data, traverses the Q intermediate personnel structure data, and obtains future personnel structure data based on the intermediate personnel structure data and the personnel flow value prediction, and finally calculates the structural risk value based on the future personnel structure data, and optimizes the Q personnel adjustment strategies based on the structural risk value and a preset intelligent optimization algorithm. In this way, this embodiment predicts the future personnel structure data through the personnel flow value and the intermediate personnel structure data, thereby solving the problem in the prior art that it is difficult to dynamically predict the personnel structure, optimizes the personnel adjustment strategy based on the structural risk value, and effectively avoids the potential risks caused by personnel mobility, thereby improving the enterprise management efficiency and optimizing resource allocation.

[0105] Example 2

[0106] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a large model-based enterprise data processing system. For details not provided in this embodiment, please refer to the description of the relevant parts in Embodiment 1. The system includes:

[0107] Data processing module: used to obtain the initial personnel structure data and Q personnel adjustment strategies of the target enterprise, and obtain the corresponding Q intermediate personnel structure data according to the initial personnel structure data and the Q personnel adjustment strategies, wherein the initial personnel structure data includes initial age structure data, initial personnel ratio data and initial job distribution data;

[0108] In this embodiment, the initial personnel structure data represents the current human resource composition and distribution of the target enterprise, the initial age structure data refers to the proportion of employees of different age groups in the total number of employees, the initial personnel proportion data refers to the proportion of employees of each department in the target enterprise in the total number of employees, and the initial position distribution data refers to the distribution ratio of the number of employees in each position in the target enterprise in the total number of employees. The above-mentioned age groups can be divided according to the same interval, for example, with every 10 years as an interval, employees are divided into age groups such as 20-30 years old, 30-40 years old, 40-50 years old, 50-60 years old, etc., so as to intuitively reflect the distribution ratio of different age groups in the enterprise. It can be understood that different types of target enterprises will result in different departments under the target enterprises, which can be determined according to actual conditions. Similarly, different types of target enterprises will lead to different position types, and this embodiment does not limit this.

[0109] Structure prediction module: used to obtain the personnel change data of the target enterprise, calculate the personnel turnover value based on the personnel change data, traverse Q intermediate personnel structure data, and predict the future personnel structure data based on the intermediate personnel structure data and the personnel turnover value;

[0110] In this embodiment, the personnel change data includes but is not limited to the number of employees joining, the number of employees leaving, and the number of employees transferred. It should be noted that the number of employees joining refers to the number of employees who have signed formal labor contracts or short-term employment agreements with the target enterprise and started to perform their job responsibilities, the number of employees leaving refers to the number of employees who have left due to contract termination, retirement, etc., and the number of employees transferred includes the number of employees whose positions have been adjusted due to transfer, promotion or demotion. In the above, taking the number of employees joining as an example, the number of employees joining can be the average number of employees joining in recent months, so as to reflect the recruitment stability and human resource replenishment efficiency of the target enterprise within a certain time period. Similarly, the average number of employees leaving in recent months can be taken to reflect the staff turnover rate and resignation trend of the target enterprise within a certain time period; for the number of employee transfers, the average number of employee transfers in recent months can be taken to reflect the frequency of internal position adjustment and the flexibility of personnel flow of the target enterprise.

[0111] Methods for calculating staff turnover value based on staff change data include:

[0112] According to the personnel change data, a corresponding personnel change matrix is ​​constructed, and the personnel change matrix is ​​multiplied element by element with the preset weight matrix to obtain a weighted change matrix, and the personnel flow value is determined based on the weighted change matrix.

[0113] Methods for predicting future personnel structure data based on intermediate personnel structure data and personnel turnover values ​​include:

[0114] The intermediate personnel structure data and personnel flow values ​​are input into the pre-built structure prediction model to obtain the future personnel structure data.

[0115] The construction method of the structural prediction model includes:

[0116] A training sample set is obtained, which includes historical intermediate personnel structure data and historical personnel flow values, and preset sliding step size and sliding window length; the training sample set is converted into multiple training samples using a sliding window method, and the training samples are used as the input of the initial model. The historical intermediate personnel structure data after the predicted sliding step size is used as the output of the initial model, and the subsequent historical intermediate personnel structure data of each training sample is used as the prediction target. The initial model is trained with the prediction accuracy as the training target; a structural prediction model is generated to predict future personnel structure data based on the intermediate personnel structure data and personnel flow values, and the initial model is an LSTM model.

[0117] Strategy optimization module: used to calculate the structural risk value according to the future personnel structure data, optimize Q personnel adjustment strategies based on the structural risk value and the preset intelligent optimization algorithm to obtain the optimal adjustment strategy;

[0118] The future personnel structure data include future age structure data, future personnel proportion data and future job distribution data. The future age structure data refers to the proportion of employees of different age groups in the total number of employees of the target enterprise at the predicted time point, reflecting the trend and changes in the age distribution of the enterprise in the future. The future personnel proportion data refers to the proportion of employees of each department in the total number of employees of the target enterprise at the predicted time point, reflecting the personnel distribution of each department in the future enterprise. The future job distribution data refers to the distribution ratio of the number of employees in each position in the total number of employees of the target enterprise at the predicted time point, reflecting the allocation of human resources in job settings of the future enterprise.

[0119] Methods for calculating structural risk values ​​based on future personnel structure data include:

[0120] The age groups, positions and departments in the future personnel structure data are taken as nodes, and the future age structure data, future personnel proportion data and future position distribution data are taken as edges to construct a personnel structure diagram. The Herfindahl-Hirschman index and Shannon entropy value of the personnel structure diagram are calculated, and the difference between the Herfindahl-Hirschman index and the Shannon entropy value is taken as the structural risk value.

[0121] Example 3

[0122] like Figure 4As shown, this embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a large model-based enterprise data processing method provided by the above methods.

[0123] Since the electronic device introduced in this embodiment is an electronic device used to implement a big model-based enterprise data processing method in the embodiment of the present application, based on the big model-based enterprise data processing method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as technical personnel in this field implement the electronic device used in the big model-based enterprise data processing method in the embodiment of the present application, it belongs to the scope of protection of this application.

[0124] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0125] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0127] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0130] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0131] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for processing enterprise data based on a large model, characterized in that: include: Obtaining initial personnel structure data and Q personnel adjustment strategies of the target enterprise, and obtaining corresponding Q intermediate personnel structure data according to the initial personnel structure data and the Q personnel adjustment strategies, wherein the initial personnel structure data includes initial age structure data, initial personnel ratio data, and initial job distribution data; Obtain the target company's personnel change data, calculate the personnel turnover value based on the personnel change data, traverse Q intermediate personnel structure data, and predict the future personnel structure data based on the intermediate personnel structure data and the personnel turnover value; The structural risk value is calculated according to the future personnel structure data, and Q personnel adjustment strategies are optimized based on the structural risk value and the preset intelligent optimization algorithm to obtain the optimal adjustment strategy.

2. The enterprise data processing method based on a large model according to claim 1, characterized in that: The personnel change data includes the number of employees joining, the number of employees leaving, and the number of employees transferring. The method for calculating the personnel turnover value based on the personnel change data includes: According to the personnel change data, a corresponding personnel change matrix is ​​constructed, and the personnel change matrix is ​​multiplied element by element with the preset weight matrix to obtain a weighted change matrix, and the personnel flow value is determined based on the weighted change matrix.

3. The enterprise data processing method based on a large model according to claim 2 is characterized in that: The weighted variation matrix includes: WCM= ; Among them, WCM is represented as a weighted change matrix, Characterized as The number of employees joining each department, Characterized as The number of employees leaving the department, Characterized as Number of employee transfers per department, Characterized as The weight corresponding to the number of employees joining each department, Characterized as The weight corresponding to the number of employees leaving each department, Characterized as The weight corresponding to the number of employee transfers in each department.

4. The enterprise data processing method based on a large model according to claim 3 is characterized in that: The method for determining the staff turnover value based on the weighted change matrix includes: FLV= ; In the formula, FLV is the personnel turnover value, Indicates The department in The weighted change value under the change type, Indicates Total number of employees leaving the department, All are weight factors, and the change types include employee joining, employee leaving and employee transfer.

5. The enterprise data processing method based on a large model according to claim 4 is characterized in that: The method for predicting future personnel structure data based on intermediate personnel structure data and personnel turnover value includes: Input the intermediate personnel structure data and personnel flow values ​​into the pre-built structure prediction model to obtain the future personnel structure data; The construction method of the structural prediction model includes: A training sample set is obtained, which includes historical intermediate personnel structure data and historical personnel flow values, and presets a sliding step size and a sliding window length; the training sample set is converted into multiple training samples using a sliding window method, and the training samples are used as the input of the initial model. The historical intermediate personnel structure data after the predicted sliding step size is used as the output of the initial model, and the subsequent historical intermediate personnel structure data of each training sample is used as the prediction target. The initial model is trained with the prediction accuracy as the training target; a structural prediction model is generated to predict future personnel structure data based on the intermediate personnel structure data and personnel flow values.

6. The enterprise data processing method based on a large model according to claim 1 is characterized in that: The future personnel structure data includes future age structure data, future personnel ratio data and future job distribution data. The method for calculating the structural risk value based on the future personnel structure data includes: The age groups, positions and departments in the future personnel structure data are taken as nodes, and the future age structure data, future personnel proportion data and future position distribution data are taken as edges to construct a personnel structure diagram. The Herfindahl-Hirschman index and Shannon entropy value of the personnel structure diagram are calculated, and the difference between the Herfindahl-Hirschman index and the Shannon entropy value is taken as the structural risk value.

7. The enterprise data processing method based on a large model according to claim 6 is characterized in that: The intelligent optimization algorithm is a whale optimization algorithm. Based on the structural risk value and the preset intelligent optimization algorithm, Q personnel adjustment strategies are optimized. The method for obtaining the optimal adjustment strategy includes: S301: Define the initial number of whales as Q and the maximum number of iterations , each initial whale individual is represented as a personnel adjustment strategy, and the random value rand is a random number sampled from a uniform distribution of [0, 1]; S302: Obtain the structural risk value corresponding to the personnel adjustment strategy, and use the structural risk value as the target fitness value of the initial whale individual; S303: When the random value rand is less than 0.5, a shrinking and encircling strategy is performed; when the random value rand is greater than or equal to 0.5, a spiral hunting strategy is performed; S304: Repeat the above step S303 to continuously update the personnel adjustment strategy until the maximum number of iterations is reached , output the current optimal personnel adjustment strategy, and take the optimal personnel adjustment strategy as the optimal adjustment strategy.

8. The enterprise data processing method based on a large model according to claim 7 is characterized in that: The method for performing the shrinking and surrounding strategy comprises: ; in, For the next generation of whale positions, is the current whale position, To pursue the target location, is the shrinkage coefficient of the shrinkage and encirclement strategy, is the control factor of the shrinking and encircling strategy, is the current iteration number.

9. An enterprise data processing system based on a big model, used to implement an enterprise data processing method based on a big model as claimed in any one of claims 1 to 8, characterized in that: include: Data processing module: used to obtain the initial personnel structure data and Q personnel adjustment strategies of the target enterprise, and obtain the corresponding Q intermediate personnel structure data according to the initial personnel structure data and the Q personnel adjustment strategies, wherein the initial personnel structure data includes initial age structure data, initial personnel ratio data and initial job distribution data; Structure prediction module: used to obtain the personnel change data of the target enterprise, calculate the personnel turnover value based on the personnel change data, traverse Q intermediate personnel structure data, and predict the future personnel structure data based on the intermediate personnel structure data and the personnel turnover value; Strategy optimization module: used to calculate the structural risk value according to the future personnel structure data, and optimize Q personnel adjustment strategies based on the structural risk value and the preset intelligent optimization algorithm to obtain the optimal adjustment strategy.

10. 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, the enterprise data processing method based on a large model as described in any one of claims 1 to 8 is implemented.

Images